business-model-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill guides the agent to research and synthesize data from external public sources, which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Research workflows described in SKILL.md and the references/ folder involve retrieving and analyzing data from external URLs, analyst reports, and financial filings.
- Boundary markers: The instructions suggest using evidence tags (e.g., [source]) and structured tables to isolate data, but do not explicitly instruct the agent to disregard instructions embedded within the retrieved content.
- Capability inventory: The skill itself does not contain executable code, subprocess calls, or network scripts, but is designed to be used with the agent's built-in web search and retrieval tools.
- Sanitization: The skill does not provide mechanisms for sanitizing or filtering external content before it is interpolated into the agent's context.
Audit Metadata