pencil-ios-design

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes a link to an external GitHub repository (github.com/partme-ai/full-stack-skills) cited as the source for the design tools. This is a static reference for documentation purposes and does not involve automated code execution or package installation.
  • [INDIRECT_PROMPT_INJECTION]: The workflow incorporates data from external sources to guide the design process, which represents a potential injection surface.
  • Ingestion points: The skill retrieves data from the get_guidelines and get_style_guide tools to inform the design requirements.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between design instructions and potentially malicious content embedded in external guidelines.
  • Capability inventory: The skill utilizes batch_design, open_document, and set_variables to modify the design canvas and document state.
  • Sanitization: No sanitization or validation logic is specified for the data returned by the guidelines or style guide tools.
  • [SAFE]: The skill's primary function is to facilitate UI design by providing a structured set of instructions based on established design systems (Apple HIG). No evidence of credential theft, unauthorized network access, obfuscation, or persistence mechanisms was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:32 PM