cloudflare
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes logic for processing data from external sources such as incoming emails and documentation search results. This establishes an attack surface where an LLM could potentially be influenced by instructions embedded in that data. Ingestion points include message streams in references/email-workers/api.md and documentation tool outputs in SKILL.md. Boundary markers and explicit sanitization are not shown in the integration snippets, as they focus on functional logic.
- [EXTERNAL_DOWNLOADS]: The documentation references various official Cloudflare SDKs and well-known developer tools (e.g., wrangler, pulumi, aws-sdk). These resources originate from trusted organizations and well-known services and do not pose a security risk.
Audit Metadata