HOL LogoGuard

Explore HOL

  • HOL home
  • AI agent registry
  • AI plugins
  • Open standards
  • HOL members

Guard product

  • Guard overviewLocal security and control for AI agents and the tools they use.
  • FeaturesRuntime protection, policy routing, review, and evidence.

Explore Guard

  • Product previewWalk through Guard surfaces in read-only demo mode.
  • ComparisonCompare Guard with native controls and AI security vendors.

AI tools

  • All AI toolsEvery supported AI tool and how Guard applies policy to it.
  • Codex
  • Claude Code
  • Cursor
  • Antigravity CLI
  • OpenCode
  • Hermes
  • OpenClaw
  • GitHub Copilot CLI
  • Antigravity
  • Kimi
  • Grok
  • Pi / Oh My Pi
  • Zcode

Extensions

  • All extensionsBrowse command and MCP coverage with owners and stated limits.
  • Command coverageShell command protection across clouds, databases, backups, and packages.
  • MCP server coverageSee how Guard maps risk state across MCP tools and servers.
  • Core safetyThe safety floor listings that ship with Guard.
  • Data and resilienceBackup and storage command protection.
  • Cloud and infrastructureAWS, Azure, GCP, Kubernetes, and more.

Security

  • AI security hubSecurity research, advisories, and agent safety coverage.
  • AI tool securitySecurity profiles for each supported coding agent.
  • Safe labsHands-on attack simulations with safe boundaries.
  • Redacted warningsReal blocked actions with sensitive details removed.
  • AdvisoriesCoordinated disclosure reports for AI tooling.
  • Active CVEsSearch active CVEs affecting AI tooling.

Learn

  • Security guidesPractical guides for securing AI agent workflows.
  • DocsInstall, configure, and operate Guard with confidence.
  • ResearchPublished security research, benchmarks, and methodology.

Community

  • ReleasesVersion history, shipped changes and upgrade notes.
  • ContributorsThe people and contributions behind HOL Guard.
  • AffiliatesShare Guard with your audience and earn from referrals.
  • SponsorKeep agent security open: sponsor a project, place a banner, or fund a security initiative.
PricingEnterpriseOpen AppInstall Guard
  1. Guard
  2. Security
  3. CVEs
  4. CVE 2026 55557 browse mcp arbitrary file write via unconfined
HOL Guard

Public security guidance for teams protecting AI harnesses, MCP servers, skills, prompts, and local tool execution.

Install Guard

AI Security

  • Prompt injection
  • MCP security
  • OWASP MCP mapping
  • Supply chain

Resources

  • Trust packet
  • Harness setup
  • Redacted warnings
  • Safe labs

Product

  • Install Guard
  • Pricing
  • Open dashboard
Guard
  • Guard Overview
  • Releases
  • Contributors
  • Install Guard
  • Pricing
Docs
  • Documentation Index
  • Developer Hub
  • API Reference
  • Root OpenAPI
  • Registry OpenAPI
  • Run in Postman
  • Standards
  • Submit ERC-8004 Contract
  • Feature Your Agent
Best Plugins
  • Browse Plugins
  • Plugin Launches
  • Best Claude Plugins
  • Best Codex Plugins
  • Best Grok Plugins
  • Best Kimi Plugins
  • Best DeepSeek Plugins
  • Best Antigravity Plugins
  • Best MCP Servers
  • Best Cursor Plugins
  • Best OpenCode Plugins
Best Agents
  • Best ERC-8004 Agents
  • Best Virtuals Agents
  • Best MCP Servers
  • Best A2A Agents
  • Best x402 Payable
  • All Categories
Community
  • Telegram
  • X
More
  • About HOL
  • Contact
  • Blog
  • GitHub
  • Privacy
  • Terms of Service
Settings

Copyright © 2026 HOL DAO LLC. All rights reserved.

Back to active CVEs
High · CVSS 0.0CVE-2026-55557GHSA-M9MQ-7M7Q-XC6P

browse-mcp: Arbitrary file write via unconfined download and state pathsCVE-2026-55557

Answer in brief

CVE-2026-55557 records a High severity (CVSS 0.0) vulnerability in browse-mcp: Arbitrary file write via unconfined download and state paths. The current sources do not mark it as known exploited. The current feed maps That1Drifter/browse-mcp (generic), browse-mcp (npm). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Aug 25, 2026Updated Sep 9, 2026Source checked Oct 9, 2026First seen by HOL Aug 25, 2026Material review Sep 9, 2026
Upstream Advisory

Record context

Vulnerability class
Path Traversal
EPSS
Not reported
CWE IDs
CWE-22
Source
CVE List V5
Source checked
Oct 9, 2026
References
6 linked sources
Open source record

Key facts

Risk
High · CVSS 0.0
Exploitation
Not marked as known exploited
Affected software
2 mapped packages or products
Fix availability
Available

Why this deserves its current priority

CVSS is 0.0. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps That1Drifter/browse-mcp (generic), browse-mcp (npm). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
PackageAffected rangeFixed version
That1Drifter/browse-mcpgeneric< 0.8.2Not reported
browse-mcpnpm<=0.8.10.8.2

Recommended response

  1. 1Check inventory. Check lockfiles and deployed manifests for That1Drifter/browse-mcp, browse-mcp.
  2. 2Review the reported fix. Update browse-mcp to 0.8.2 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

  1. Published upstream

    Aug 25, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  2. Source modified

    Sep 9, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  3. First seen by HOL

    Aug 25, 2026

Sources and claim methodology

  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
Upstream source description

browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download writes a fetched response body to join(save_dir, filename) without validating the caller-controlled save_dir, while browser_save_state and browser_load_state honor a caller-controlled path unchanged. A malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page, can choose an arbitrary save_dir or state path and a URL whose response body becomes attacker-controlled file contents, allowing writes to any path the process can reach, including ~/.bashrc, autostart entries, or cron files, and potentially leading to host code execution. The force_fetch fallback also uses a raw fetch() that bypasses the BROWSE_MCP_ALLOWED_ORIGINS origin fence. This issue is fixed in version 0.8.2.

Quoted source text, attributed separately from HOL analysis.

Related CVEs

  • Contao: Path traversal in the images controllerAlso CWE-22
  • Shiny for Python - Path traversal in bookmark restoreAlso CWE-22
  • MariaDB: `qc_info` plugin can do OOB reads if query contains \0Same generic ecosystem
  • MariaDB: mysql_json plugin OOB readsSame generic ecosystem
  • MariaDB: environment injection via wsrep bootstrap in the mariadb.service fileSame generic ecosystem
  • MariaDB Connector/C: libmariadb allowed cleartext password leakage on TLS hostname verification failureSame generic ecosystem