client-discovery

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill consists of prompt-based instructions for generating a discovery plan.
  • [SAFE]: The skill lacks executable code, network access, and file system interactions, preventing data exfiltration or system compromise.
  • [SAFE]: While the skill ingests user-provided data (prospect info, offering details), it lacks the capabilities (e.g., shell access, network tools) required to exploit indirect prompt injection. Ingestion points: SKILL.md (prospect, offering, decision needs). Boundary markers: Absent. Capability inventory: None. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:26 PM
Security Audit — agent-trust-hub — client-discovery