widgetkit
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, defining how the AI agent should route specific WidgetKit developer queries to internal knowledge base contracts.
- [NO_CODE]: No scripts, binary files, or command execution patterns were found within the skill or its frontmatter.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied queries about software implementation, representing a minimal indirect injection surface. However, the skill lacks any tool access or file-writing capabilities that would allow an injection to be exploited.
- Ingestion points: User queries regarding implementation details of Widget, TimelineProvider, and WidgetCenter.
- Boundary markers: None identified.
- Capability inventory: The skill does not define any allowed-tools or executable scripts.
- Sanitization: None present, as the output is limited to selecting internal documentation.
Audit Metadata