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