kanxiang

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as an image analysis assistant using vision tools to extract features from face, palm, or body photos provided by the user.
  • [COMMAND_EXECUTION]: There is no automated command execution within the skill logic. The README provides manual installation steps for users involving standard git operations.
  • [DATA_EXPOSURE]: The skill does not access sensitive local files or environment variables. It processes user-uploaded data within the designated session context.
  • [OBFUSCATION]: All instructions, prompts, and reference documents are provided in plain text (Markdown) without any encoding or hidden payloads.
  • [EXTERNAL_DOWNLOADS]: The skill relies on local reference files within the project directory and does not perform runtime network requests or download external scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:12 AM
Security Audit — agent-trust-hub — kanxiang