wecomcli-media

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines clear, restricted procedures for using the wecom-cli tool. It strictly prohibits the use of general-purpose shell or execution environments, limiting the agent to specific, validated commands for media handling. All operations trace back to the vendor's intended infrastructure.
  • [SAFE]: Data protection measures are explicitly included, such as instructions to avoid exposing internal identifiers like media_id and file_path to the end-user, and rejecting potentially unsafe inputs like URLs in place of media identifiers.
  • [SAFE]: The skill recognizes and correctly handles security-restricted resources (e.g., links from the well-known work.weixin.qq.com domain), instructing the agent to guide the user toward authorized client-side viewing rather than attempting to bypass security controls.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:33 AM
Security Audit — agent-trust-hub — wecomcli-media