pay-via-agent-wallet

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design.
  • Ingestion points: Data enters the agent context from external third-party sources via the circle services search, circle services inspect, and circle services pay tools, as well as curl requests to URLs discovered in the marketplace.
  • Boundary markers: The instructions lack explicit delimiters or guidance to ignore potentially malicious instructions embedded in the data retrieved from external services.
  • Capability inventory: The skill utilizes tools with significant capabilities, including blockchain wallet operations, CLI execution, and arbitrary network requests.
  • Sanitization: There is no evidence of sanitization or structural validation performed on the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:39 AM