skills/openclaw/skills/ima-skill/Gen Agent Trust Hub

ima-skill

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands and local helper scripts (node, python3, curl, iconv) to perform API interactions, validate file metadata, and ensure correct text encoding before transmission.
  • [DATA_EXFILTRATION]: The skill is designed to read user-provided API credentials from environment variables or local configuration files (~/.config/ima/) to authenticate requests sent to the official IMA API endpoint at ima.qq.com.
  • [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it can fetch and process content from external URLs and user-uploaded files; however, it includes instructions to filter sensitive content and requires explicit user confirmation for potentially destructive operations like appending to existing notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:03 PM
Security Audit — agent-trust-hub — ima-skill