skill-creator

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides utility scripts to manage the skill development lifecycle.
  • scripts/deploy.sh automates the installation of skills into agent-specific configuration directories like ~/.claude/skills.
  • scripts/validate.sh performs automated checks on skill metadata, structure, and file references.
  • [EXTERNAL_DOWNLOADS]: The documentation refers to external tools and repositories for skill discovery and publication.
  • Mentions the use of the npx skills utility for adding skills from the community.
  • References the author's own repository STIFLEUR390/agent-skills for skill publication.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for generating and validating other skills based on user input.
  • Ingestion points: The scripts/validate.sh script reads and parses user-created SKILL.md files.
  • Boundary markers: Templates use standard Markdown headers and YAML frontmatter as structural boundaries.
  • Capability inventory: The skill uses Bash and Write tools to manage files and execute validation/deployment logic.
  • Sanitization: The validation script implements regex-based checks for field formats and length constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:11 AM
Security Audit — agent-trust-hub — skill-creator