release-check
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes standard development commands including git, cargo, and gh (GitHub CLI) to verify project readiness. These operations are limited to auditing the repository state and do not involve unauthorized data exfiltration or privilege escalation.
- [PROMPT_INJECTION]: Ingests local project files to generate a summary report, creating an indirect prompt injection surface.
- Ingestion points: docs/content/docs/, TODO.md, todo/, and SECURITY_EXCEPTIONS.md.
- Boundary markers: None.
- Capability inventory: Subprocess calls to git, gh, and cargo in SKILL.md.
- Sanitization: None detected.
- Assessment: These operations are consistent with the skill's primary purpose of auditing project files. The risk is minimized as the data is sourced from the local repository and the subsequent reporting steps are benign.
Audit Metadata