postgres-optimization
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill is primarily documentation-based, offering legitimate SQL snippets for database performance tuning. Analysis of all provided files found no evidence of prompt injection, credential theft, or malicious command execution.
- Indirect Prompt Injection (SAFE): 1. Ingestion points: Untrusted data enters via the 'query' and 'table' inputs defined in SKILL.md. 2. Boundary markers: None are explicitly defined in the provided files. 3. Capability inventory: The skill requests the 'run_terminal_cmd' capability in its metadata. 4. Sanitization: No sanitization logic is present in the markdown text. The overall risk is low as the tool is intended for performance analysis.
- Metadata (INFO): The repository includes a 'skill-snitch-report.md' which asserts the skill's safety. In accordance with security protocols, this report was treated as data rather than a conclusion, and the final verdict was determined by independent analysis of the skill's functionality.
Audit Metadata