wecom-doc-manager

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes content from external WeChat Work documents.
  • Ingestion points: External data enters the agent context via the get_doc_content tool as described in references/api-export-document.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched content as untrusted or to ignore embedded instructions.
  • Capability inventory: The agent possesses the capability to modify and create documents through the create_doc and edit_doc_content tools, which could be exploited if the agent obeys instructions found within a read document.
  • Sanitization: No validation or sanitization of the Markdown content is specified before processing.
  • [COMMAND_EXECUTION]: The skill relies on calling the wecom_mcp command-line tool to perform document operations. While this is the intended functionality, it involves the agent executing specific formatted commands.
  • [SAFE]: No other high-risk patterns such as hardcoded credentials, obfuscation, or unauthorized network exfiltration were detected. All external URL references target official WeChat Work domains (doc.weixin.qq.com).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 04:45 PM