ideagram

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs local file operations such as reading, writing, and indexing SVG files within the "~/.ideagram/undraw" directory. This is standard behavior for the tool's stated purpose.
  • [SAFE]: Python scripts such as "recolor_undraw.py", "recolor_svg.py", and "extract_component.py" use standard string and regex operations to modify SVG content. There is no usage of dangerous functions like eval() or exec() on untrusted input.
  • [SAFE]: External dependencies mentioned, such as "cairosvg" and "Pillow", are well-known and standard libraries used for image rendering and processing.
  • [SAFE]: The "validate_assets.py" script includes a safety check to ensure that SVG/XML files are well-formed and do not contain illegal characters that could break strict renderers.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found in any of the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:19 PM
Security Audit — agent-trust-hub — ideagram