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, andtasks-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) andtasks-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, andcanvas-createtools. - 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