slidev-multi-agent

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The sync-references.mjs script fetches markdown documentation from official project domains, including sli.dev, openai.com, claude.com, and openclaw.ai. This is a legitimate maintenance function to provide the agent with up-to-date documentation.
  • [COMMAND_EXECUTION]: The skill includes several bash scripts (slidev-init.sh, slidev-dev.sh, slidev-build.sh, slidev-export.sh, slidev-theme-eject.sh, and slidev-theme-scaffold.sh) that wrap Slidev CLI commands. These scripts resolve the CLI path through a shared utility _slidev_common.sh, prioritizing local installations before falling back to global commands or npx.
  • [REMOTE_CODE_EXECUTION]: The slidev-init.sh and slidev-export.sh scripts facilitate the installation of standard project dependencies (@slidev/cli, @slidev/theme-default, and playwright-chromium) via npm. These packages are official components of the Slidev and Playwright ecosystems and are necessary for the skill's stated purpose.
  • [PROMPT_INJECTION]: No malicious instructions, bypass markers, or safety overrides were detected in the SKILL.md file or the supporting documentation.
  • [DATA_EXFILTRATION]: No sensitive file access patterns or unauthorized network transmissions of local data were identified in the provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM