cloudflare-workers-expert
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of edge functions that ingest untrusted data from the Fetch API (Request object). This creates an attack surface for indirect prompt injection if the worker's processing logic or output is subsequently consumed by other AI agent systems without adequate sanitization.
- Ingestion points: The
fetch(request)handler defined in the code examples inSKILL.md. - Boundary markers: No explicit instruction for delimiters or 'ignore embedded instructions' warnings for incoming request data.
- Capability inventory: KV Namespace access, HTTP header modification, and asynchronous task execution via
ctx.waitUntil(). - Sanitization: The provided examples do not include explicit sanitization or validation of the request body or headers before processing.
Audit Metadata