postgresql-18-docs
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a workflow for ingesting and processing content from external documentation pages, which presents an attack surface for indirect prompt injection if those sources were compromised. However, the skill specifically targets the official PostgreSQL documentation, which is a well-known and trusted domain.
- Ingestion points: Official documentation pages under
postgresql.org/docs/18/and user-supplied search queries. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the fetched documentation content.
- Capability inventory: The skill allows the agent to generate SQL code, server configuration examples (e.g.,
postgresql.conf,pg_hba.conf), and documentation-grounded explanations. - Sanitization: There are no explicit instructions for sanitizing or filtering the content retrieved from the external documentation site.
Audit Metadata