the-feed-watch
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions. 1. Ingestion points: Product feed exports, Merchant Center diagnostics, live product page URLs, and ledger files. 2. Boundary markers: The instructions do not define delimiters or isolation for external content. 3. Capability inventory: The skill requires the agent to read local files and fetch content from storefront URLs. 4. Sanitization: No sanitization or validation of ingested data is specified.
- [NO_CODE]: The skill consists only of markdown instructions and metadata, with no scripts or binaries provided for analysis.
Audit Metadata