render-scaling
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides explicit instructions for the agent to fetch and read external Markdown documents from the render.com website. Ingesting this data without boundary markers or sanitization creates a potential surface for indirect prompt injection.
- Ingestion points: SKILL.md and several reference files contain instructions to fetch and read external documents.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions found within the fetched documentation.
- Capability inventory: The agent is directed to use network tools like curl to retrieve content and then read it into its context.
- Sanitization: There are no steps provided for sanitizing or validating the content of the fetched documents.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to retrieve documentation from the official render.com domain. These downloads are from a well-known service provider and are documented as a way to ensure the agent has access to current platform specifications.
Audit Metadata