skills/akindu23/my-agent-skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: Fetches syntax highlighting components from Cloudflare's well-known CDN for use in generated HTML lessons.
  • [COMMAND_EXECUTION]: Suggests a scoped local server command for lesson previews using Python's built-in module, which is limited to the workspace directory.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from the web via search tools (Ingestion points: RESOURCES.md). It lacks explicit boundary markers for this data in lessons but mandates a 'discover then verify' workflow (Sanitization: Verification). Its capabilities are limited to generating local files and suggesting user-executed commands (Capability inventory: File writing, local server suggestion).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 11:45 AM
Security Audit — agent-trust-hub — teach