skills/zgid123/skills/slidevjs/Gen Agent Trust Hub

slidevjs

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mandates the installation of specific NPM packages, @alphacifer/slidev-academic-theme and @alphacifer/slidev-addon-theme. These are functional dependencies required to implement the visual theme described in the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the user's local repository, including directory structures and package.json manifests, to determine how to apply changes. While this is a standard operating procedure for scaffolding tools, it constitutes an indirect injection surface if local project files were to contain adversarial content.
  • Ingestion points: Inspection of the local repository structure and package.json manifest (SKILL.md, Workflow steps 1 and 2).
  • Boundary markers: Not present; the agent is instructed to read existing files directly into context.
  • Capability inventory: The skill can modify package.json, create new directories, and write Markdown and image files (SKILL.md, Workflow steps 3 and 5).
  • Sanitization: No specific sanitization or filtering logic is defined for the content read from the project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 05:31 PM
Security Audit — agent-trust-hub — slidevjs