Answer in brief
CVE-2026-66065 records a High severity (CVSS 8.4) vulnerability in Ouroboros: Untrusted project .env can still reach RCE via omitted execution-routing keys (Incomplete fix of CVE-2026-47211). The current sources do not mark it as known exploited. The current feed maps Q00/ouroboros (generic), ouroboros-ai (pip), ouroboros-ai (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.4. 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.
The current feed maps Q00/ouroboros (generic), ouroboros-ai (pip), ouroboros-ai (pypi). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| Q00/ouroborosgeneric | <0.42.1 | 0.42.1 |
| ouroboros-aipip | <=0.42.0 | 0.42.1 |
| ouroboros-aipypi | >=0 <0.42.1 | 0.42.1 |
Published upstream
Aug 3, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 23, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jun 19, 2026
Ouroboros is a local-first runtime for AI coding agents that records their actions and applies user-defined policies to constrain behavior. Versions prior to 0.42.1 have an incomplete denylist. Several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command execution by shipping a .env (auto-loaded at import, with no review step). The CVE-2026-47211 fix added _UNTRUSTED_ENV_DENYLIST to stop an untrusted project-directory .env from redirecting execution, but it did not account for all keys. The backend config-home and MCP/plugin roots bypass the approval gate by pointing the nested agent, MCP servers, and plugin roster at attacker config. Other variables re-enable blocked local transports, replace sub-agent prompts, switch backends, and lower tool approval classes, further weakening the approval gate. This issue has been fixed in version 0.42.1.
Quoted source text, attributed separately from HOL analysis.