bigquery-pipeline-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a strictly analytical role for the agent, focused on identifying risks in BigQuery pipelines. It does not perform network operations, access sensitive local files, or request elevated privileges.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebases, which constitutes an indirect prompt injection surface.
- Ingestion points: The skill processes code provided in the agent's context (referenced in SKILL.md instructions).
- Boundary markers: None explicitly defined in the instructions to delimit analyzed code from the agent's logic.
- Capability inventory: The skill generates text-based reports and suggested patches; it does not have the capability to execute the analyzed code, write to the filesystem, or perform network requests.
- Sanitization: No sanitization or validation of the input codebase is specified, though the outcome is limited to a textual report which reduces the risk of exploitation.
Audit Metadata