skills/fubits1/svelte-skills/editing/Gen Agent Trust Hub

editing

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill mandates the use of standard development tools, including pnpm lint:file (knip) for export validation and npx markdownlint-cli for documentation checks.
  • [COMMAND_EXECUTION]: A defined workflow for visual refactors uses Playwright MCP to automate browser interactions and capture screenshots in the /tmp directory for comparison.
  • [PROMPT_INJECTION]: The skill processes source code comments which serves as a potential surface for indirect prompt injection. Ingestion points: Project source files (.ts, .svelte, .js, .md). Boundary markers: Not implemented. Capability inventory: File system writes, CLI execution, and browser automation. Sanitization: No sanitization is performed on ingested comment content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 02:54 PM
Security Audit — agent-trust-hub — editing