skills/charikshith/skills/flowchart/Gen Agent Trust Hub

flowchart

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches typography assets from Google Fonts when the optional 'handwritten' style is requested. This is a well-known service used for legitimate design purposes.
  • [COMMAND_EXECUTION]: The instructions direct the agent to run a local validation script (scripts/validate.py). This script uses the Playwright library to automate a browser instance, checking the generated HTML for layout issues like overlapping shapes or clipped text and rendering preview images. This is a standard quality assurance practice.
  • [INDIRECT_PROMPT_INJECTION]: As the skill ingests user-provided text to populate flowchart nodes and labels, it technically has an ingestion surface for untrusted data. However, the risk is mitigated as the output is a static HTML artifact, and the validation script checks for structural integrity and JavaScript errors prior to delivery.
  • [DYNAMIC_EXECUTION]: The validation script utilizes a browser's evaluation capability to execute a static block of JavaScript designed to calculate bounding boxes and detect element collisions within the generated SVG. The code being executed is hardcoded within the script and does not incorporate unsanitized external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 11:54 AM