wisemind-ai

Pass

Audited by Gen Agent Trust Hub on Jun 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to interface with a local-first knowledge workbench. All network operations are directed to http://127.0.0.1:38221, which is the user's own machine. This is consistent with the stated purpose of the skill.
  • [COMMAND_EXECUTION]: The skill instructions utilize curl to perform HTTP requests to the local API. These commands are strictly for CRUD operations on notes, files, and cards, and do not involve executing arbitrary shell code or accessing sensitive system files.
  • [EXTERNAL_DOWNLOADS]: The documentation references an installation command via npx that targets the author's own GitHub repository (Chris8891/wisemind-ai). This is a standard procedure for installing agent skills and does not involve untrusted third-party scripts.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns were detected. The instructions provided to the agent are functional and focus on API interaction protocols rather than attempting to bypass safety guidelines or override core behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 2, 2026, 03:06 AM