release
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands through
gitand the GitHub CLI (gh) to automate repository management, including checking immutability settings, pushing to the main branch, managing tags, and creating releases. - [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to process external data from documentation files (
docs/development/quality-gates.md, etc.), commit messages, and changelogs. The risk is mitigated by explicit verification steps, such as grounding names in source code rather than memory and requiring signed tags.
Audit Metadata