project-flow-ops
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and metadata. No code, scripts, or subprocess executions were found in the provided file.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub, such as PR comments and issue descriptions, which represents an inherent surface for indirect prompt injection. The instructions mitigate this by explicitly directing the agent to use full diffs rather than summaries and to prioritize product direction over automated triggers.
- [DATA_EXPOSURE_&_EXFILTRATION]: While the skill coordinates data between GitHub and Linear, it does so within the context of the user's intended tools and does not exhibit patterns of exfiltration to unauthorized third-party domains.
Audit Metadata