makepad-widgets

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a documentation and coding assistant for the Makepad UI framework. It contains standard Rust code snippets and architectural patterns for UI components.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from external reference files (e.g., ./references/widgets-core.md). This constitutes an untrusted data ingestion surface common to documentation skills.
  • Ingestion points: Reference files located at ./references/widgets-core.md, ./references/widgets-advanced.md, and ./references/widgets-richtext.md are read into the agent's context based on instructions in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the reference files are present.
  • Capability inventory: The skill is designed for code generation and answering queries; it does not contain subprocess execution or network operations.
  • Sanitization: No sanitization or validation of the content within the reference files is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 01:25 PM