skills-creator
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill's instructions mention the
!commandsyntax, explaining its use for shell command execution at load time. This is provided as educational context for users developing their own components and does not constitute a malicious implementation within this skill. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of new files by gathering user requirements and reading project-specific configuration files, creating a potential surface for indirect injection.
- Ingestion points: User requirements (Phase 1),
.claude-plugin/marketplace.json, andCLAUDE.md(Phase 3). - Boundary markers: The instructions do not define specific delimiters for separating user-provided content from generated boilerplate.
- Capability inventory: The skill uses file system tools to create directories (
plugins/<plugin>/skills/<skill-name>/) and write multiple markdown and JSON files. - Sanitization: There are no explicit instructions for sanitizing or escaping user input before it is written to the generated component files.
Audit Metadata