drawing-diagrams

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a local Python script (mermaid-encode.py) to process user-provided diagram code. Analysis of the script confirms it only uses Python standard libraries (argparse, base64, json, sys, zlib) and does not perform any network operations or file system access beyond reading from stdin.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a shell command to pipe diagram code into the local encoder script and then to the system's browser opener (open or xdg-open). This is the intended primary purpose of the skill and does not involve any privileged escalation or dangerous shell patterns.
  • [EXTERNAL_DOWNLOADS]: No external packages or remote scripts are downloaded. The skill relies entirely on the provided local script and the user's pre-installed Python 3 environment.
  • [DATA_EXFILTRATION]: The skill generates URLs for mermaid.live. These URLs contain the diagram state encoded in the fragment identifier (after the #), which is processed client-side by the mermaid.live web application. No data is sent to a third-party server by the skill itself; the user explicitly chooses to open the URL in their own browser.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 07:40 AM