expert-skill-creator

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and reference files providing architectural guidance and quality standards for skill development.- [EXTERNAL_DOWNLOADS]: Includes URLs to official Anthropic documentation and Claude Code resources for reference; no suspicious or non-standard remote content is fetched.- [DATA_EXFILTRATION]: The skill provides specific instructions on how to detect and prevent data leaks (PII/secrets) in developed skills, showing a strong security posture.- [REMOTE_CODE_EXECUTION]: Mentions the use of helper subagents for research tasks and structured scripts for deterministic operations, which are standard practices within the agent ecosystem.- [COMMAND_EXECUTION]: Describes the 'dynamic context injection' feature (using !command syntax) found in other skills but does not execute any shell commands itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 01:12 PM
Security Audit — agent-trust-hub — expert-skill-creator