render-cron-jobs
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions create an ingestion surface for indirect prompt injection by directing the agent to fetch and process external documentation.\n
- Ingestion points:
SKILL.md(Current documentation retrieval section) andreferences/private-networking.md/references/service-types.md(shared blocks) instruct the agent to retrieve content fromrender.comURLs.\n - Boundary markers: Absent. There are no instructions for the agent to treat the fetched content as untrusted or to ignore any embedded instructions or commands.\n
- Capability inventory: The skill enables the agent to use
curlfor network requests and to author Render Blueprint configurations containing shell commands (buildCommand,startCommand).\n - Sanitization: Absent. No validation or sanitization of the remote content is required before the agent incorporates it into its context.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from a well-known service domain.\n
- Evidence: The skill directs the agent to use
curlto fetch the latest Markdown documentation fromhttps://render.com/docs/private-network.mdandhttps://render.com/docs/service-types.md.
Audit Metadata