ai-forge-create
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-tool for drafting other skills. All instructions focus on token economy, logic structure, and quality gates.
- [SAFE]: The inclusion of a validation script (
scripts/validate-metadata.cjs) is a best practice for ensuring metadata consistency and preventing malformed frontmatter. The script itself performs local string validation and uses no external dependencies or network calls. - [SAFE]: All external references and platform documentation target well-known and trusted services including Anthropic, Microsoft (GitHub Copilot), OpenAI, and Google.
- [SAFE]: The skill explicitly warns against prompt injection risks, specifically advising users to avoid XML angle brackets in metadata to prevent accidental injection into system prompts.
- [SAFE]: Guidelines for scripts emphasize error handling, deterministic output, and descriptive feedback, which are security-positive practices for agentic environments.
Audit Metadata