project-flow-ops
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data from GitHub and Linear, which could contain malicious instructions designed to influence the agent's triaging decisions.
- Ingestion points: GitHub issue or PR state, review comments, and linked issues (identified in the 'Read the public surface first' section of SKILL.md).
- Boundary markers: The instructions do not define clear boundaries or 'ignore' instructions for the data being ingested.
- Capability inventory: The skill is empowered to classify work (Merge, Port/Rebuild, Close, Park) and create or update items in Linear based on the processed content.
- Sanitization: There are no specific instructions for sanitizing or escaping the content retrieved from GitHub or Linear before it is evaluated by the agent.
Audit Metadata