xerahs-release-bump-tag
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8). Evidence: 1. Ingestion points: The agent is instructed in
SKILL.mdandrun-release-sequence.shto fetch and inspect potentially untrusted GitHub Actions logs (gh run view --log). 2. Boundary markers: No markers or 'ignore' instructions are provided when processing the log content. 3. Capability inventory: The agent is empowered to modify repository files, commit changes, and push to remote branches to 'fix root cause'. 4. Sanitization: No sanitization or filtering of log content is implemented before the agent analyzes it. - [COMMAND_EXECUTION]: The skill performs significant local command execution including Git operations (
git pull,git commit,git push,git tag) and GitHub CLI operations (gh run,gh release). These are necessary for its primary purpose of release orchestration but grant the agent broad control over the project's version control and release infrastructure.
Audit Metadata