acp-checkout-rest

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches canonical specifications and developer guides from official OpenAI and Stripe resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data such as items, addresses, and buyer information.
  • Ingestion points: Input data for the Create and Update flows described in SKILL.md.
  • Boundary markers: There are no explicit instructions for the use of delimiters or 'ignore' commands to prevent processing of instructions embedded in the data.
  • Capability inventory: The skill has access to tools including Read, Write, Bash, and WebFetch.
  • Sanitization: The provided instructions do not include specific data sanitization or validation requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:32 PM