ci-failure-triage
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted external data sources.
- Ingestion points: The workflow requires reading and analyzing CI logs, failing job outputs, and recent merge history (SKILL.md).
- Boundary markers: The skill does not specify any delimiters or instructions for the agent to distinguish its primary goals from potential commands embedded in the log data.
- Capability inventory: The triage process involves diagnosing root causes and proposing fixes, which necessitates the interpretation of data that could be manipulated by an attacker to influence the agent's conclusions.
- Sanitization: There are no requirements or steps provided to sanitize, filter, or validate the content of the external logs before they are processed.
Audit Metadata