pretty-html-ppt

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The maintenance script scripts/validate_template_library.py executes local Python scripts (copy_template.py and validate_deck.py) using subprocess.run to verify the integrity of the template library.
  • [PROMPT_INJECTION]: The skill processes untrusted user data (Markdown, Feishu docs, text notes) and interpolates it into HTML templates, creating a surface for indirect prompt injection.
  • Ingestion points: External documents and user-provided descriptions are ingested in SKILL.md to populate slides.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the model to ignore embedded commands within the user-provided source material.
  • Capability inventory: The skill can write to the local filesystem and inject JavaScript runtimes into generated HTML files.
  • Sanitization: There is minimal sanitization of user-provided content during interpolation into HTML templates, which could lead to unintended script execution in the generated browser-based presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 03:57 AM
Security Audit — agent-trust-hub — pretty-html-ppt