siyu-market-research
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from public web search results, which is an untrusted external source.\n
- Ingestion points: Sections I and II instruct the agent to use web search tools to gather data on vendors, pricing, and company status (SKILL.md).\n
- Boundary markers: The instructions do not specify the use of boundary markers to separate search content from the agent's instructions.\n
- Capability inventory: The skill produces a 'Market Research Snapshot' intended to be the sole source of truth for downstream skills, creating a path for instruction propagation.\n
- Sanitization: There are no instructions for sanitizing or filtering instructions that might be embedded in the retrieved web content.
Audit Metadata