skills/zgid123/skills/slidev/Gen Agent Trust Hub

slidev

Warn

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of external Node.js packages: @alphacifer/slidev-academic-theme and @alphacifer/slidev-addon-theme. These packages are hosted on public registries and are not associated with a verified or trusted organization provided in the analysis parameters.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using various package managers (npm, pnpm, yarn) to install the required dependencies. Instructions under the 'Dependencies' section direct the agent to detect the environment and add these third-party packages to the manifest files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided seminar content (titles, articles, speaker info) and interpolates it directly into Markdown templates. There are no clear boundary markers or sanitization steps mentioned to prevent malicious instructions in user data from influencing the agent's behavior during the file creation process.
  • Ingestion points: User prompts describing seminar structure, timing, and speaker data (e.g., slides.md template placeholders).
  • Boundary markers: Absent.
  • Capability inventory: File system writing (creation of .md files) and package installation via subprocesses.
  • Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 24, 2026, 06:24 AM
Security Audit — agent-trust-hub — slidev