omarchy-panel-overlay
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an
open(payloadJson)entry point for processing external structured data. This creates a surface where malicious instructions could be embedded in payloads to influence agent behavior during UI construction. - Ingestion points: The
open(payloadJson)method is defined inSKILL.mdandreferences/lifecycle-and-windows.mdas the primary way to provide data to the UI. - Boundary markers: The instructions explicitly warn to treat payload JSON as untrusted input and parse it defensively.
- Capability inventory: No high-risk capabilities such as shell command execution, sensitive file access, or network requests are included in the provided code examples.
- Sanitization: The skill mandates strict validation, capping of data sizes, and ignoring unknown keys to sanitize incoming data.
Audit Metadata