soia-pkm-reading-plan

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to install external dependencies via npx skills add. This includes tools from Tencent (well-known service) and the vendor's own repository (soia-team/soia-open-skills).
  • [COMMAND_EXECUTION]: Installation and configuration require the execution of shell commands such as npx, claude plugin install, and manual configuration of YAML files.
  • [CREDENTIALS_UNSAFE]: The skill documentation references the use of WEREAD_API_KEY. It explicitly instructs users to manage this sensitive information through private configuration files (config.yml) or environment variables, avoiding exposure in logs or shared vaults.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (articles, URLs). It mitigates potential injection risks by implementing a mandatory 'checkpoint' phase where the agent must present a summary to the user for confirmation before performing any file-writing operations (Obsidian note creation).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:47 AM
Security Audit — agent-trust-hub — soia-pkm-reading-plan