market-research
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as market reports, competitor websites, and investor activity. This creates an attack surface where malicious instructions embedded in those external documents could influence the agent's behavior.
- Ingestion points: The skill instructs the agent to collect data from "product reality", "public datasets", "reports", and "investor dossiers" in the SKILL.md Common Research Modes section.
- Boundary markers: The instructions do not define specific delimiters or security warnings to help the agent distinguish between researcher instructions and content found in the data sources.
- Capability inventory: The skill contains only natural language instructions and does not define executable code or tool-calling logic within this file.
- Sanitization: There are no instructions for sanitizing or filtering content gathered from external sources before it is processed by the agent.
Audit Metadata