my-wiki

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a suite of local Python scripts to perform deterministic tasks such as initializing the directory structure, searching content, and generating knowledge graphs. These scripts are self-contained and use only the Python standard library.
  • [EXTERNAL_DOWNLOADS]: The graph.py script generates an HTML report that loads the Mermaid JavaScript library from cdn.jsdelivr.net (a well-known content delivery network). This is used for rendering diagrams in a web browser and is a standard implementation for this functionality.
  • [DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill reads from and writes to user-specified local directories to manage the wiki content.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from URLs and local files for processing. While this introduces a potential surface for indirect prompt injection, the skill uses structured templates and boundary markers to mitigate accidental obedience to instructions within the source material.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:54 AM
Security Audit — agent-trust-hub — my-wiki