investigating-ci-failures

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from CI failure logs and error signatures, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: Data is ingested from the engineering_analytics_ci_failures warehouse view and through the engineering-analytics-ci-failure-logs and engineering-analytics-run-failure-logs MCP tools.
  • Boundary markers: The instructions do not include explicit boundary markers or guidance for the agent to treat log content strictly as data and ignore any embedded natural language instructions.
  • Capability inventory: The skill utilizes execute-sql for querying warehouse data and interacts with GitHub APIs through mentioned tools.
  • Sanitization: The process does not specify any sanitization, filtering, or escaping of the log content before the agent analyzes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:58 AM
Security Audit — agent-trust-hub — investigating-ci-failures