postgresql-17-docs
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates documentation lookups from a trusted, well-known source (postgresql.org). No executable code, dangerous commands, or unauthorized network operations were found in the skill's instructions or references.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for user queries regarding documentation, creating a surface for potential indirect prompt injection from user input or processed documentation content. However, the skill lacks the necessary capabilities (such as file-writing, code execution, or credential access) to escalate such an injection into a security threat. Mandatory Evidence Chain: 1. Ingestion points: User queries handled in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No file-system writes, no code execution (exec/eval), and no arbitrary network operations. 4. Sanitization: Absent.
Audit Metadata