soia-pkm-bootstrap-vault-ima

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a bundled Python script, scripts/preflight_sync.py, to perform a local privacy check. This script ensures that files containing potential secrets or improper sensitivity labels are not synchronized.\n- [EXTERNAL_DOWNLOADS]: Provides instructions for installing dependencies from the author's official GitHub organization (soia-team) and downloading the official Tencent ima client from ima.qq.com. These are trusted or well-known sources.\n- [DATA_EXFILTRATION]: Orchestrates the transfer of local vault data to the Tencent ima cloud service. The skill incorporates multiple safeguards, including an exclusion list for sensitive files (like .env and .git) and a requirement for explicit sensitivity labeling, to ensure user privacy.\n- [PROMPT_INJECTION]: The skill reads local Markdown files to verify metadata. The analysis script is designed to report only metadata types and risk codes back to the agent, avoiding the ingestion of raw note content that could contain malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:05 AM
Security Audit — agent-trust-hub — soia-pkm-bootstrap-vault-ima