market-sizing
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is instructed to ingest and process potentially untrusted external content.
- Ingestion points: According to SKILL.md, the agent analyzes user-provided market research, industry reports, financial data, and results retrieved via web search.
- Boundary markers: The instructions do not define explicit delimiters or include directives for the agent to ignore instructions embedded within the data being analyzed.
- Capability inventory: The skill leverages web search tools to collect and analyze market data.
- Sanitization: There are no defined procedures for sanitizing, validating, or filtering external content before it is incorporated into the agent's context.
Audit Metadata