skills/denoland/skills/deno-guidance/Gen Agent Trust Hub

deno-guidance

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The skill contains negative constraints and scope boundaries (e.g., 'Never Show Deprecated Syntax', 'only applies to Deno-specific questions'). These are intended to guide the AI's output quality and relevance rather than bypass safety filters or override core agent instructions.
  • External Downloads (SAFE): The skill promotes the use of standard package managers (deno add, jsr:, npm:). It specifically discourages the use of deprecated URL-based imports, which improves the security posture of the resulting code by favoring versioned and checksummed packages from JSR/npm.
  • Command Execution (SAFE): References to Deno CLI commands like deno run, deno fmt, and deno lint are standard development workflow instructions. It correctly highlights Deno's permission system (e.g., --allow-net) as a security feature to prevent unauthorized resource access.
  • Data Exfiltration (SAFE): No patterns involving access to sensitive local files (SSH keys, AWS creds) or unauthorized network transmissions were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM