cloudflare-workers-ai

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes implementation templates for RAG (Retrieval Augmented Generation) and vision models that process untrusted external data.
  • Ingestion points: templates/ai-embeddings-rag.ts retrieves data from a Vectorize database, and templates/ai-vision-models.ts performs network fetches using user-provided URLs.
  • Boundary markers: While templates/ai-embeddings-rag.ts includes instructions to the model to use specific context, the templates lack explicit sanitization or escaping of the ingested content before interpolation into prompts.
  • Capability inventory: The skill templates demonstrate the ability to perform network requests (fetch), execute LLM inference (env.AI.run), and write to persistent storage (env.BUCKET.put).
  • Sanitization: The references/best-practices.md file correctly identifies the need for input sanitization and provides examples, but these practices are not enforced in the primary functional templates, leaving a vulnerability surface for developers who use the templates as-is.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:47 PM