local-market-research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard practices for market research, focusing on data retrieval from public platforms. All tools referenced (e.g.,
sandbase_describe_tool) are vendor-specific resources consistent with the author's identity. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including social media and review platforms.
- Ingestion points: External data is retrieved from Google Maps, Xiaohongshu, Weibo, and general web searches via Tavily (SKILL.md).
- Boundary markers: The skill does not explicitly define delimiters to isolate external content from the agent's core instructions.
- Capability inventory: The skill is limited to data retrieval capabilities; there are no file-writing, shell execution, or network-post tools defined in the workflow.
- Sanitization: The instructions do not specify content sanitization, but they do mandate separating factual observations from interpretation, which serves as a logical mitigation against following instructions embedded in research data.
Audit Metadata