lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): Vulnerable to Indirect Prompt Injection.
- Ingestion points: Processes local codebase files (Instruction 1) and external web search results for company research (Instruction 3).
- Boundary markers: Absent. There are no delimiters or warnings to treat external content strictly as data.
- Capability inventory: The skill leverages file reading and web search tools to analyze projects and identify market leads.
- Sanitization: No input validation or escaping mechanisms are defined for the data retrieved from external sources.
Audit Metadata