revealjs-skill

Warn

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's configuration and body point to an external GitHub repository (github.com/ryanbbrown/revealjs-skill) for its primary functionality, which is not a verified or well-known source.
  • [COMMAND_EXECUTION]: The instructions explicitly direct the AI agent to run installation commands (/plugin marketplace add) and suggest using the ! shell-execution prefix in tools like Claude Code to facilitate the installation of external code.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing user-provided content into interactive presentations.
  • Ingestion points: User-supplied data and instructions used to generate slide content (as per the 'What it does' section).
  • Boundary markers: No boundary markers or 'ignore' instructions are present to delimit user data from the generation process.
  • Capability inventory: Marketplace plugin installation; shell-execution via ! prefix; file system access to check installation paths (~/.design-agent-skills/).
  • Sanitization: No evidence of validation, escaping, or sanitization of input data before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — revealjs-skill