authoring-skills

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOW
Full Analysis
  • [Prompt Injection] (SAFE): The skill provides meta-instructions for creating other skills. No attempts to bypass safety filters or override core agent behavior were detected.- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive local paths, or network communication code exists in the documentation.- [Remote Code Execution] (SAFE): The file contains only Markdown and YAML frontmatter. There are no shell commands, remote downloads, or package installations.- [Obfuscation] (SAFE): All text is clearly readable with no hidden characters, Base64 encoding, or homoglyph-based evasion techniques.- [Indirect Prompt Injection] (SAFE): The skill does not define tools for processing untrusted external content, and its instructions are purely structural for the agent's internal skill organization.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 09:08 AM