competitive-intelligence-analyst
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill package is composed entirely of Markdown documentation and a basic JSON metadata file.\n
- No scripts (Python, Node.js, Shell) or binary executables are present in the provided files.\n
- The skill operates solely by providing a persona and structured workflow for the AI agent to follow during dialogue.\n- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves analyzing content from external sources which could potentially contain malicious instructions.\n
- Ingestion points: Step 2 (Competitor Deep Dive) instructs the agent to gather data from external websites, review platforms (G2/Capterra), and social media.\n
- Boundary markers: Absent; the instructions do not specify delimiters for external content.\n
- Capability inventory: None; the skill does not use any tools for file writing, system modification, or network requests beyond standard browser/search capabilities.\n
- Sanitization: Absent; the skill relies on the agent's internal safety filters.
Audit Metadata