market-sizing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and does not contain any executable scripts, shell commands, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data which is a standard surface for indirect prompt injection. 1. Ingestion points: The skill processes user-provided market research, industry reports, and the $ARGUMENTS variable. 2. Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the user-provided data. 3. Capability inventory: The skill relies on web search and text analysis capabilities. 4. Sanitization: No data sanitization or validation mechanisms are implemented in the prompt instructions.
- [SAFE]: The skill includes supplemental links to a well-known product management educational site for further reading; these are informational and do not involve remote code execution.
Audit Metadata