slides

Warn

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: MEDIUMMETADATA_POISONINGCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [METADATA_POISONING]: The author field in SKILL.md is set to claudekit, which is inconsistent with the provided author context nextlevelbuilder. Misaligned metadata can be used to misrepresent the origin of a skill.
  • [COMMAND_EXECUTION]: The reference files (copywriting-formulas.md, layout-patterns.md, and slide-strategies.md) contain instructions for the agent to execute shell commands using Python.
  • [DYNAMIC_EXECUTION]: These instructions specifically target a script named search-slides.py located at .claude/skills/design-system/scripts/. Since the script is not included in the package and resides in an external directory, its behavior cannot be verified, posing a risk of executing unintended or malicious code present on the local system.
  • [EXTERNAL_DOWNLOADS]: The HTML template in references/html-template.md includes a reference to the Chart.js library from the well-known JSDelivr CDN (https://cdn.jsdelivr.net/npm/chart.js@4.4.1/dist/chart.umd.min.js). This is a legitimate resource for the skill's stated purpose of data visualization.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 3, 2026, 02:58 PM
Security Audit — agent-trust-hub — slides