postgresql-best-practices-cloudbase
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided application code and SQL queries for architectural review, which creates an ingestion surface for untrusted data that could contain malicious instructions.
- Ingestion points: User-supplied SQL scripts, TypeScript/JavaScript code, and environment metadata analyzed in SKILL.md and throughout the reference files.
- Boundary markers: The instructions do not specify the use of strict delimiters or specific 'ignore' markers when the agent processes these external code snippets.
- Capability inventory: The skill utilizes tools such as queryPgDatabase for executing SQL and queryEnv for retrieving environment metadata.
- Sanitization: The documentation indicates that the queryPgDatabase tool provides some safety by restricting execution to read-only SQL and rejecting tokens such as ANALYZE.
Audit Metadata