acp-product-feed
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions specify fetching product feed field specifications and submission endpoint details from OpenAI's official developer documentation (https://developers.openai.com/commerce/product-feeds/spec).
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data which represents a theoretical attack surface for indirect prompt injection.
- Ingestion points: Fetches content from an external documentation URL and performs web searches for updated feed requirements.
- Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded in the fetched documentation.
- Capability inventory: The skill is configured with tools that allow for file system writes, edits, and shell command execution (Bash).
- Sanitization: No sanitization, validation, or filtering of the external content is implemented before processing.
Audit Metadata