third-party-listings
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, specifically app store listings and directory profiles. \n
- Ingestion points: The workflow involves fetching live metadata, descriptions, and reviews from the Apple App Store, Google Play, and other third-party discovery platforms as specified in references/store-audit.md and references/directory-workflow.md. \n
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the processed external data. \n
- Capability inventory: The skill identifies and scores listing dimensions, generates metadata, and creates submission packets. It explicitly mandates human authorization before performing any state-changing actions like submissions or payments. \n
- Sanitization: The instructions do not define methods for sanitizing or validating external content before it is incorporated into the agent's context.
Audit Metadata