project-flow-ops
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues, pull requests, and review comments. This data could contain instructions that attempt to influence the agent's decision-making process during triage or classification tasks.
- Ingestion points: GitHub issue/PR state, review comments (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: The skill has instructions to create/update Linear tasks and post public resolutions back to GitHub (SKILL.md).
- Sanitization: None identified.
Audit Metadata