release-guard
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: A detailed analysis of the skill's logic and instructions found no evidence of malicious patterns, such as prompt injection, data exfiltration, or obfuscation. The skill's primary purpose is to enhance the security and stability of the release process.
- [COMMAND_EXECUTION]: The skill is authorized to use the GitHub CLI (
gh) and Git to perform repository status checks and release operations. These commands are used to query PR state, verify CI/CD logs, and create tags, which are appropriate and expected actions for a release management tool. - [PROMPT_INJECTION]: The skill exhibits an indirect injection surface because it processes external repository data. 1. Ingestion points: The skill reads PR metadata and CI/CD run statuses via
gh pr viewandgh run list. 2. Boundary markers: The skill utilizes structured JSON output (--json) andjqfiltering to isolate data. 3. Capability inventory: The skill has the ability to tag commits and create releases. 4. Sanitization: Safety is maintained by relying on specific boolean-like fields (e.g.,state: CLOSED,conclusion: success) rather than interpreting free-text descriptions or comments.
Audit Metadata