fix-ci
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through external CI data processing.
- Ingestion points: The workflow instructs the agent to ingest data from
gh pr checksoutput, GitHub Actions logs, and 'external check links' (SKILL.md). - Boundary markers: Absent; there are no delimiters or warnings to ignore instructions within the ingested data, which could allow malicious logs to hijack the agent's behavior.
- Capability inventory: The agent has the capability to write files ('Apply the smallest safe fix') and execute commands ('Push') (SKILL.md).
- Sanitization: Absent; the content from logs and external links is not validated or filtered before the agent processes it for 'actionable errors'.
Audit Metadata