presentation-generator

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references frontend assets including Reveal.js, Mermaid.js, MathJax, and highlight.js from the well-known JSDelivr CDN (cdn.jsdelivr.net).
  • [COMMAND_EXECUTION]: The skill generates and executes Python scripts using the Matplotlib library to render architecture diagrams as described in references/matplotlib-guide.md.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted external data (projects and papers) to generate its output.
  • Ingestion points: Step 1 in SKILL.md involves analyzing arbitrary project files and research papers.
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions in source material.
  • Capability inventory: The agent can execute shell commands for diagram generation (references/matplotlib-guide.md) and write complex HTML/JS files (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the input source material is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:49 AM
Security Audit — agent-trust-hub — presentation-generator