composing-grid-canvases

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as canvas layouts, component source code, and user comment threads via tools like canvas-layout-get, canvas-source-retrieve, and tasks-comments-retrieve. This creates a potential surface for indirect prompt injection if malicious instructions are embedded in these external sources.
  • Ingestion points: Data is ingested through canvas-layout-get (SKILL.md) and tasks-comments-retrieve (SKILL.md) to inform layout updates and component creation.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate or sanitize instructions that might be contained within the retrieved data.
  • Capability inventory: The skill possesses writing and code generation capabilities through canvas-layout-patch, canvas-layout-publish, and canvas-create tools.
  • Sanitization: The instructions do not mention any specific sanitization or filtering logic for the ingested content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:39 AM
Security Audit — agent-trust-hub — composing-grid-canvases