lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are focused entirely on business research and lead qualification. All described steps align with its stated purpose. No malicious commands, obfuscation, or data exfiltration patterns were detected.
- [PROMPT_INJECTION]: The skill has an exposure surface for indirect prompt injection due to its core functionality of reading external web data and local codebase files. 1. Ingestion points: External search results, company websites, job postings, and local product source code. 2. Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for external content. 3. Capability inventory: The skill utilizes file-reading (to analyze codebases) and web-searching capabilities. 4. Sanitization: No specific content validation or sanitization steps are documented for the ingested data. This is classified as safe as it is a low-risk exposure inherent to the skill's primary research function.
Audit Metadata