skills/dwmkerr/claude-toolkit/slides/Gen Agent Trust Hub

slides

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as npm install and make to manage the lifecycle of presentation decks.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs verified Slidev CLI and theme packages from the official NPM registry.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it reads external project files like README.md to generate content, which could contain hidden instructions for the agent.
  • Ingestion points: Reads project documentation and README files via the agent's file system tools.
  • Boundary markers: The instructions do not define clear boundaries or safety prompts to isolate untrusted source data from the slide generation task.
  • Capability inventory: The skill can create and modify files (slides.md, package.json, Makefile) and execute shell commands (npm, npx).
  • Sanitization: The skill does not validate or sanitize the retrieved documentation before using it in the slide generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:49 AM
Security Audit — agent-trust-hub — slides