lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were detected. The skill's behavior is consistent with its stated purpose of lead research and business development assistance.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data from company websites and local codebases. However, this is a standard risk for research tools and the skill contains no instructions to bypass safety filters or execute unauthorized actions. Evidence of ingestion points includes instructions to 'analyze the codebase' and 'search for companies matching the criteria' in SKILL.md. No specific sanitization or boundary markers are defined for this external data.
Audit Metadata