wecomcli-disk

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to manage files on Corporate WeChat (WeCom) Disk using the wecom-cli utility. It follows best practices by defining a specific tool scope and providing clear instructions on tool selection based on file types.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from external API calls (file metadata and search results). It addresses the risk of indirect prompt injection through a dedicated 'Security Hint' section that instructs the agent to ignore any commands or operational requests embedded in the data and to protect sensitive tokens or credentials.
  • Ingestion points: File lists, search results, and metadata returned by wecom-cli operations defined in SKILL.md.
  • Boundary markers: Includes a 'Security Hint' at the end of the instructions to delineate between data and instructions.
  • Capability inventory: File system access (upload/download) and network operations performed via the wecom-cli tool as described in SKILL.md.
  • Sanitization: Relies on explicit agent instructions to treat returned content as data rather than commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:48 AM