skills/hocgin/agent-skills/wenyan-cli/Gen Agent Trust Hub

wenyan-cli

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: Documented usage examples encourage passing sensitive secrets (appId, appSecret, api-key, and tokens) directly as command-line arguments, which can result in exposure within shell history files or process monitoring.
  • [COMMAND_EXECUTION]: The skill's functionality is centered around executing the 'wenyan' CLI tool with user-provided or remote data.
  • [EXTERNAL_DOWNLOADS]: The tool allows downloading content from external URLs for processing via the -f or --file flag, introducing dependencies on untrusted remote sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local or remote sources, providing an attack surface for indirect prompt injection. Ingestion points: Markdown content fetched from remote URLs or local files. Boundary markers: None identified. Capability inventory: Ability to perform network requests to WeChat and third-party servers, and write rendered HTML to the local file system. Sanitization: No validation or sanitization of the ingested Markdown content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:25 AM
Security Audit — agent-trust-hub — wenyan-cli