skills/tonone-ai/tonone/clause-recon/Gen Agent Trust Hub

clause-recon

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill is designed to process sensitive legal contracts and has access to network-enabled tools such as WebFetch. However, tool usage is constrained to the primary purpose of fetching regulatory guidance, and no logic for unauthorized data transmission was identified.
  • [PROMPT_INJECTION]: The skill processes untrusted data from both external web sources and local project documents, creating a surface for indirect prompt injection.
  • Ingestion points: Project contracts and regulatory websites (SKILL.md, Step 1).
  • Boundary markers: None specified to differentiate data from instructions.
  • Capability inventory: Access to Bash, Write, and WebFetch tools.
  • Sanitization: No explicit validation or sanitization of ingested content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:34 AM
Security Audit — agent-trust-hub — clause-recon