re0-release
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage the release lifecycle, including Git operations (commit, tag, push) and filesystem moves (mv).
- [COMMAND_EXECUTION]: The workflow relies on executing project-specific CLI auditing tools such as sip, shower, factchk, mandela, ssotize, and re0.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pending code diffs and repository documentation, which presents an injection surface.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: git diffs, SKILL.md files, and README files. Boundary markers: Human confirmation required before committing and pushing (Steps 6 and 8). Capability inventory: Git CLI access and file system write access to project configuration files. Sanitization: No explicit sanitization of ingested diff content is specified.
Audit Metadata