lead-research-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill exhibits vulnerability to Indirect Prompt Injection (Category 8).\n
  • Ingestion points: Step 1 of the instructions requires the agent to analyze the user's codebase to understand the product and its features.\n
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore embedded commands within the analyzed code files.\n
  • Capability inventory: The agent possesses file system read access for codebase analysis and web search capabilities for lead qualification.\n
  • Sanitization: Absent. No validation or escaping logic is defined for the content extracted from the local repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:05 PM