build-champ-triage
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection Surface]: The skill instructs the agent to analyze external data, including pull request changes, build logs, and commit histories.
- Ingestion Points: The agent ingests data from user-provided build URLs, raw build logs, and GitHub Pull Request (PR) content.
- Boundary Markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its internal logic and potentially untrusted content found within logs or PR descriptions.
- Capability Inventory: The agent uses this information to analyze root causes and draft summary messages for the team. It does not appear to have file-write or code-execution capabilities in this context.
- Sanitization: No specific sanitization or filtering of external content is mentioned before the analysis step. This creates a surface where malicious content embedded in a PR description or a test's error log could attempt to influence the agent's triage summary.
Audit Metadata