agentic-product-prototyping
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill describes a workflow for building scrapers that ingest untrusted data from external URLs.
- Ingestion points: External URLs in Example 2 (SKILL.md).
- Boundary markers: No delimiters or instructions to ignore embedded commands are suggested.
- Capability inventory: The skill explicitly advises granting agents Shell access, SQL access, and File editors.
- Sanitization: No mention of sanitizing or validating external content before processing.
Audit Metadata