discover-market-sizing
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of prompt instructions and documentation for market analysis. It contains no executable scripts, shell commands, or network operations outside of the explicitly mentioned platform tools (
WebFetch,WebSearch). - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection because it is designed to ingest data from external websites using web-fetching tools.
- Ingestion points: External market reports and data retrieved via
WebSearchandWebFetchtools. - Boundary markers: The instructions emphasize citing specific sources (publication name, year, page number) and assigning source-graded confidence labels, which encourages the agent to verify data rather than blindly follow instructions within the data.
- Capability inventory: The skill is restricted to read-only operations and does not possess capabilities to write files or execute code.
- Sanitization: No explicit sanitization logic is provided in the instructions; the skill relies on the agent's internal processing and the requirement for multi-framework triangulation to identify anomalies.
Audit Metadata