competitor-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external competitor data, such as marketing pages and reviews, which represents a potential attack surface for indirect prompt injection. * Ingestion points: Market data and competitor information provided via user input or project files. * Boundary markers: None explicitly defined to separate untrusted content from agent instructions. * Capability inventory: Tool access is restricted to Read, Glob, and Grep for local file operations. * Sanitization: No specific sanitization or escaping of external data is implemented.
- [SAFE]: The skill includes references to well-known business strategy and educational resources. * References framework documentation from Harvard Business Review (hbr.org). * References strategy tools from Strategyzer (strategyzer.com).
Audit Metadata