lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from multiple sources, creating an injection surface.
- Ingestion points: The skill explicitly instructs the agent to 'analyze the codebase to understand the product' (SKILL.md) and perform external web searches for companies and leads.
- Boundary markers: None detected. The instructions do not include specific delimiters or warnings to ignore instructions embedded in the analyzed code or search results.
- Capability inventory: The skill primarily uses read-only search and file-reading capabilities. No dangerous file-write, network exfiltration, or shell execution capabilities were identified in the provided files.
- Sanitization: No explicit sanitization or filtering of external content is mentioned in the instructions.
Audit Metadata