skills/wontakkim/skills/wontak/Gen Agent Trust Hub

wontak

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters. The skill focuses strictly on developer style guidelines.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials or sensitive file paths were detected. Code examples use standard environment variables (e.g., REDIS_URL, PAYMENT_API_KEY) as placeholders within illustrative snippets.
  • Obfuscation (SAFE): The content is clear and uses standard Markdown formatting. No hidden characters, Base64 encoding, or homoglyph attacks were found.
  • Remote Code Execution (SAFE): The skill mentions package managers like uv, pnpm, and gradle within the context of build tooling and configuration, but it does not execute remote scripts or perform dangerous downloads.
  • Persistence & Privilege Escalation (SAFE): No commands related to modifying system configuration, shell profiles, or acquiring elevated permissions were detected.
  • Indirect Prompt Injection (SAFE): This skill is a static set of guidelines and does not ingest untrusted external data that could lead to downstream injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:45 PM