xhs-login
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides fallback shell instructions for the agent to decode and display QR code images in environments where graphical rendering is unavailable.
- [NO_CODE]: The skill does not bundle any scripts or binary files, relying entirely on natural language instructions and external tools.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing information returned from login status tools.
- Ingestion points: User account status and metadata returned by check_login_status.
- Boundary markers: No explicit delimiters are specified for tool outputs.
- Capability inventory: File system writes and shell execution for QR code display, cookie deletion.
- Sanitization: No specific filtering of tool-provided strings is mentioned.
Audit Metadata