hl-ci-fix
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from CI logs and GitHub PR metadata, creating a risk that malicious instructions embedded in these sources could influence the agent behavior during the fix process.
- Ingestion points: External data enters the agent context via GitHub tooling output and logs from failing CI checks referenced in SKILL.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the ingested log content.
- Capability inventory: The skill is authorized to perform source code modifications, git commits, and normal push operations (SKILL.md).
- Sanitization: Absent. There is no mention of filtering, escaping, or validating the external log content before it is processed by the agent.
Audit Metadata