skills/charikshith/skills/visualize/Gen Agent Trust Hub

visualize

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill's instructions in SKILL.md direct the agent to execute a local Python validation script (scripts/validate.py) using shell commands. This is a standard procedure within this skill's workflow to ensure the generated visuals meet quality requirements.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics to generate HTML and SVG content, which is then rendered by a headless browser in the validation step. This creates an attack surface for indirect prompt injection; however, the risk is mitigated because the browser environment is localized and the validation script uses static JavaScript to perform its checks.
  • [SAFE]: The included scripts/validate.py script performs file system operations (reading HTML, writing PNG screenshots) and launches a browser process (via Playwright) as part of its documented validation logic. These actions are consistent with the skill's stated purpose of visual verification and do not demonstrate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 11:54 AM