lead-research-assistant

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (MEDIUM): The skill relies on external web data (search results, job postings, company news) to qualify leads. * Ingestion points: External web content and search engine results extracted during lead research (File: SKILL.md). * Boundary markers: Absent. No instructions are provided to the agent to ignore embedded commands in the data it finds. * Capability inventory: Web searching, local file reading (codebase analysis), and drafting outreach strategies (File: SKILL.md). * Sanitization: Absent. Adversaries could embed malicious instructions in their public-facing web content to manipulate the lead scoring or outreach strategies generated by the agent.
  • [Data Exposure] (LOW): The skill instructs the agent to analyze the user's codebase to understand the product context. This creates a risk where internal intellectual property is processed and potentially included in queries sent to external search engines or data enrichment services during the lead research process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 05:27 AM