dbt-pr-review
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from dbt pull requests and SQL models. While this presents an attack surface where malicious instructions could be embedded in code comments, the risk is mitigated by the skill's reliance on a deterministic Rust-based engine for structural analysis rather than relying solely on raw text processing.
- Ingestion points: PR diffs, dbt manifest files, and SQL code.
- Boundary markers: Not explicitly defined in instructions, but structured tool outputs are used.
- Capability inventory: Limited to specialized analysis tools (dbt_pr_review, impact_analysis) and read-only git access.
- Sanitization: The use of a deterministic engine implies structural parsing of the code before LLM evaluation.
Audit Metadata