skill-creator
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python and Node.js scripts (init_skill.py, package_skill.py, validate-skills.cjs) designed for local file system operations. These tools automate the creation of skill structures, perform frontmatter validation, and package skills into ZIP archives within the local project environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve gathering data from external sources such as URLs and GitHub repositories. To mitigate injection risks, a 'Source-gathering security guard' protocol is implemented, which mandates inspection without execution, prohibits package installation from untrusted sources, and requires security audits for third-party code.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill documentation describes the platform-specific '!'command' syntax for executing shell commands at skill load time. The skill itself does not utilize this syntax for execution and provides safety guidelines for its use in skill development.
Audit Metadata