market-sizing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external market research, reports, and web search results. This represents a potential surface for indirect prompt injection where instructions hidden in the processed data could attempt to influence the agent's analysis.\n
- Ingestion points: Processes user-provided data and results from web searches (SKILL.md).\n
- Boundary markers: The skill does not explicitly define delimiters for untrusted data.\n
- Capability inventory: Uses web search and text processing.\n
- Sanitization: No specific filtering or sanitization of external text content is mentioned.
Audit Metadata