ci-failure-triage
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains only markdown instructions and YAML metadata. It does not include any executable code, scripts, or configurations for external tools.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze CI logs and failing job outputs, which are untrusted external data sources. Because the skill lacks tool capabilities, this ingestion surface poses no functional security risk.
- Ingestion points: CI logs and failing jobs (SKILL.md)
- Boundary markers: None provided to distinguish logs from instructions
- Capability inventory: None (no shell, network, or file tools defined)
- Sanitization: None
Audit Metadata