cloudflare-workers
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes official Cloudflare observability endpoints at observability.mcp.cloudflare.com and workers-builds.mcp.cloudflare.com for data retrieval.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Cloudflare API responses, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The skill ingests data through tools defined in SKILL.md, including list_workers, get_worker, get_worker_bindings, list_builds, get_build, and get_worker_analytics.\n
- Boundary markers: There are no boundary markers or instructions to the agent to disregard instructions embedded in the API data within SKILL.md.\n
- Capability inventory: The skill is limited to monitoring and information retrieval tools as listed in the tools table.\n
- Sanitization: No sanitization, filtering, or validation logic for the external API content is described in the provided instructions.
Audit Metadata