ascii-dither-halftone

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements logic to process external visual media, which is its primary function.
  • Ingestion points: The initAsciiVideo function in SKILL.md requests camera access using navigator.mediaDevices.getUserMedia, and imageToAscii processes image files.
  • Boundary markers: No explicit markers are used to frame the output of the dithering or ASCII algorithms.
  • Capability inventory: The skill uses browser canvas and video APIs for image manipulation.
  • Sanitization: Input data is mapped to characters or dot sizes according to the effect logic.
  • [EXTERNAL_DOWNLOADS]: The skill references a well-known 3D graphics library for post-processing.
  • Evidence: npm i three@0.168 in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:48 PM
Security Audit — agent-trust-hub — ascii-dither-halftone