prospect-research-compiler

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Prompt Injection] (MEDIUM): Vulnerable to Indirect Prompt Injection. 1. Ingestion points: External news, social media, and websites. 2. Boundary markers: Absent; no delimiters or instructions to treat external data as untrusted. 3. Capability inventory: Generates actionable recommendations and outreach templates which influence user actions. 4. Sanitization: Absent; no logic to filter or escape malicious instructions found in source data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 08:04 AM