agent-checkouts

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface related to the ingestion of data from third-party merchant pages via the Crossmint API.
  • Ingestion points: The agent is instructed to process message and responseSchema fields from the pendingUserAction object in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat API-returned strings as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill uses scripts/checkout.mjs to make network requests to the Crossmint API, which can execute payments and order placement.
  • Sanitization: The skill lacks specific sanitization or filtering of text and schema definitions returned by the merchant-controlled API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 04:37 PM
Security Audit — agent-trust-hub — agent-checkouts