view-build-logs
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches build logs from an external service (BuildBuddy), creating a vulnerability surface where malicious instructions embedded in build output or test failures could influence the agent's behavior.
- Ingestion points: Fetches logs from BuildBuddy via the
bb viewcommand (SKILL.md). - Boundary markers: None identified; no instructions are provided to the agent to treat the fetched logs as untrusted data.
- Capability inventory: The skill facilitates command execution via the
bbCLI tool to inspect logs and test outputs. - Sanitization: None identified; the skill directly fetches and presents logs for inspection without filtering or escaping.
Audit Metadata