skills/ma1orek/replay/sveltia-cms/Gen Agent Trust Hub

sveltia-cms

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the Sveltia CMS library from the unpkg CDN (a well-known service) and references the official auth-worker repository on GitHub for OAuth deployment. Evidence: SKILL.md, scripts/init-sveltia.sh, templates/cloudflare-workers/setup-guide.md.
  • [COMMAND_EXECUTION]: Includes bash scripts (init-sveltia.sh, check-versions.sh) that automate the creation of project directories, configuration files, and version inspection using npm. Evidence: scripts/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill configures content management for static sites, creating a surface where user-provided data is ingested into the agent context through Markdown, YAML, and JSON files.
  • Ingestion points: Content folders (e.g., content/posts) and configuration files defined in SKILL.md.
  • Boundary markers: None defined in project templates.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to manage the site structure.
  • Sanitization: Not explicitly present in the provided initialization scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 11:46 AM