render-private-services
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to retrieve official Markdown documentation from the render.com domain (e.g., https://render.com/docs/private-network.md) using tools like curl. This is intended to provide the agent with up-to-date platform information regarding networking, disks, and service types. Following the policy for well-known technology services, these references are documented neutrally and do not escalate the security verdict.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a mechanism for the agent to ingest and process data from external documentation URLs, creating a theoretical attack surface for indirect prompt injection.
- Ingestion points: External Markdown and HTML files fetched from render.com/docs/.
- Boundary markers: The instructions direct the agent to confirm retrieval and read the content, but do not define specific delimiters or instructions to ignore embedded commands within the fetched documents.
- Capability inventory: The skill is primarily designed for generating Render Blueprint configurations (YAML) and providing deployment advice; it does not specify arbitrary file-writing or subprocess execution capabilities on the host system.
- Sanitization: There are no explicit steps for sanitizing or validating the content of the retrieved documentation before processing.
Audit Metadata