cloudflare-r2

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (HIGH): The skill documentation and examples expose the agent to Indirect Prompt Injection risks.
  • Ingestion points: Untrusted external data enters the agent context through the use of R2 get() and list() operations on objects in R2 buckets.
  • Boundary markers: No delimiters or instructions to ignore embedded commands within retrieved objects are present in the provided TypeScript examples or documentation.
  • Capability inventory: The skill provides the agent with broad capabilities to modify storage, including put() for overwriting data, delete() for removing objects, and bucket configuration via wrangler.jsonc.
  • Sanitization: There is no evidence of sanitization, validation, or escaping of data retrieved from R2 before it is processed by the agent.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:51 AM