skills/ggglhhh/skills/slidev/Gen Agent Trust Hub

slidev

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent on using shell commands via pnpm and slidev for project creation, builds, and exports.- [EXTERNAL_DOWNLOADS]: Instructions include downloading the Playwright browser and various NPM packages for slide formatting, icons, and themes.- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by processing external Markdown files which may contain embedded instructions.
  • Ingestion points: Markdown content files and imported slides
  • Boundary markers: None specified in instructions
  • Capability inventory: Shell command execution (pnpm, slidev) and file system writes (monaco-write)
  • Sanitization: None specified in instructions- [DATA_EXFILTRATION]: Documentation describes using --remote --tunnel to expose the local development server to the internet using Cloudflare Quick Tunnels, which constitutes a data exposure risk.- [NO_CODE]: No executable scripts or source code are included in the skill; it consists entirely of Markdown instructions and references.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:15 AM