skillforge
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a development tool for scaffolding and refining agent skills. It provides clear instructions, follows progressive disclosure principles, and includes a mandatory 'Gotchas' section for reliability.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and tools from reputable sources including Anthropic's official GitHub repository, Microsoft research papers (Arxiv), and well-known developer optimization tools. These references are used for educational and benchmarking purposes.
- [COMMAND_EXECUTION]: The skill documents the use of standard development tools and scripts (such as git, bash, and helper scripts) for project scaffolding and deterministic validation. These are standard within the intended developer workflow.
- [PROMPT_INJECTION]: The skill includes instructions that involve researching external domains and processing user-provided reference materials. While this creates a surface for indirect prompt injection, it is managed through a structured verification and audit loop (defined in the 'optimize' mode) and represents standard functionality for a research-oriented development tool.
Audit Metadata