product-demand-research
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze data from untrusted external sources, including social media comments, forums, and product reviews.
- Ingestion points: The workflow involves collecting customer language from TikTok Shop, Amazon Shop pages, search results, and video transcripts as described in SKILL.md.
- Boundary markers: There are no instructions provided to delimit untrusted content or to warn the agent against executing instructions that might be embedded in the fetched data.
- Capability inventory: While the skill uses other tools for data gathering, it creates a surface where malicious instructions in a review or social post could influence the agent's analysis or output.
- Sanitization: No explicit sanitization or filtering logic is defined for the external data.
Audit Metadata