makepad-splash

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill describes the use of cx.eval() and cx.eval_with_context() to evaluate strings as Splash code at runtime, which is a high-risk capability if the input string is not strictly controlled.
  • [INDIRECT_PROMPT_INJECTION]: The skill is explicitly designed for AI-assisted workflows where the agent generates Splash code. This creates a risk where untrusted data processed by the agent could influence the logic of the generated script. Ingestion points: AI-generated UI scripts and workflow automation; Boundary markers: Documentation mentions a sandboxed environment but lacks specific prompt delimitation for data processing; Capability inventory: Network access via http object and script execution via eval; Sanitization: No specific sanitization or validation methods are documented for generated code strings.
  • [COMMAND_EXECUTION]: The skill instructs the agent to prompt the user to execute the /sync-crate-skills command if local reference documentation is missing or incomplete.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:37 PM
Security Audit — agent-trust-hub — makepad-splash