postgres
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied natural language to construct and execute SQL queries using the
psqlcommand-line utility.\n - Ingestion points: The skill accepts user input as natural language queries, as shown in the 'Usage Examples' section of SKILL.md.\n
- Capability inventory: The skill utilizes shell-based command execution via the
psqlbinary (SKILL.md) to interact with a database.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to segregate user input from the core prompt or to ignore embedded instructions.\n
- Sanitization: The skill does not implement any validation, escaping, or filtering of the natural language input before it is used to form SQL commands.
Audit Metadata