flow-ship
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository environment, including branch names, existing pull request metadata, and repository status, which could potentially contain malicious instructions.
- Ingestion points: Repository delivery rules, branch/remotes configuration, and existing change request metadata (SKILL.md).
- Boundary markers: The skill does not explicitly define delimiters or markers to isolate external data when interpolating it into prompts.
- Capability inventory: The skill can execute Git commands (commit, push, merge) and run local project scripts for linting, testing, and building (SKILL.md).
- Sanitization: There are no mentions of escaping or sanitizing external content, though it recommends passing pull request bodies via structured fields or files to reduce injection risks.
Audit Metadata