competitor-market-analyst
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions direct the agent to fetch information from external websites using search tools, which creates an attack surface for indirect prompt injection. Malicious instructions on visited sites could attempt to override the agent's behavior.
- Ingestion points: The agent ingests data from external websites via search tools and user-provided product information (SKILL.md).
- Boundary markers: No delimiters or specialized instructions are present to distinguish between instructions and potentially untrusted external data.
- Capability inventory: The skill relies on search tools for network-based data retrieval.
- Sanitization: No sanitization, validation, or filtering of the retrieved content is specified in the workflow.
Audit Metadata