skills/daveebbelaar/bama/design-kit/Gen Agent Trust Hub

design-kit

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the design/KIT.md specification file and measurements from the design-from-app tool to generate Swift source code. 1. Ingestion points: design/KIT.md template and tool output from design-from-app. 2. Boundary markers: None identified in instructions. 3. Capability inventory: The agent writes Swift files and executes local linting tools. 4. Sanitization: No explicit sanitization of the input specification is defined.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands such as tools/grid-lint.sh and grep search patterns to verify code compliance with the design kit. These are diagnostic development tools acting on local source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 10:40 PM