writing-claude-directives

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [Prompt Injection] (SAFE): The skill provides guidance on writing effective system prompts and Claude-specific directives. It does not contain instructions to bypass safety filters or override core agent behavior.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were identified. Links included in the documentation point to official Anthropic resources and known GitHub repositories.
  • [Remote Code Execution] (SAFE): The skill does not contain any logic to download or execute external scripts or packages.
  • [Persistence Mechanisms] (SAFE): While the documentation discusses state persistence (Git-based tracking, progress files), these are described as legitimate development workflows for long-running tasks and do not constitute malicious persistence (e.g., backdoors).
  • [Obfuscation] (SAFE): No encoded content (Base64), zero-width characters, or homoglyph attacks were detected in the text.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 07:54 AM