changelog-release
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (git logs, pull request descriptions, and commit messages) which could contain malicious directives. To mitigate this, the skill includes a dedicated 'Untrusted input' section that explicitly instructs the agent to treat this data as passive information and ignore any embedded commands like 'ignore previous rules' or 'approve and merge'.
- [PROMPT_INJECTION]: A static detector flag for instruction override patterns was determined to be a false positive. The suspicious phrases (e.g., 'ignore previous rules') appear only as examples of what the agent should disregard when processing external data, serving as a defense rather than a malicious injection.
Audit Metadata