Skills
skills/narumiruna/agent-skills/creating-slide-decks/Gen Agent Trust Hub

creating-slide-decks

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines workflows that involve running internal scripts such as init_presentation.py and check_contrast.py using the uv package runner. It also utilizes svglint for diagram validation.- [PROMPT_INJECTION]: The skill processes user-supplied markdown and SVG data, creating a potential surface for indirect prompt injection. Evidence: Ingestion points include slide content and SVG specifications; boundary markers are not present; capabilities include internal script execution via uv; and sanitization logic is not defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 05:19 AM
Security Audit — agent-trust-hub — creating-slide-decks