render-postgres
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to fetch the most current documentation directly from render.com using curl. These downloads target the vendor's official domain to ensure the agent has access to up-to-date platform specifications, limits, and compute plan details.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates a mechanism to read and process external documentation, which presents a surface for indirect prompt injection. This is a core part of the documentation-retrieval functionality provided by the vendor.
- Ingestion points: Remote Markdown files fetched from official render.com documentation URLs, such as compute-plans.md and private-network.md.
- Boundary markers: The instructions do not specify the use of delimiters or isolation markers for the retrieved content.
- Capability inventory: The skill utilizes MCP tools including query_render_postgres for SQL query execution (noted as read-only) and list_postgres_instances for resource discovery.
- Sanitization: There is no explicit sanitization or validation logic described for the fetched documentation content.
Audit Metadata