frontend-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes an ingestion surface for untrusted data from the local codebase to perform its design diagnosis. * Ingestion points: Reads tailwind.config files, CSS stylesheets, and component markup (SKILL.md). * Boundary markers: Lacks explicit delimiters or instructions to ignore embedded malicious instructions in the analyzed files. * Capability inventory: Employs file system search and read capabilities (glob, grep) to analyze codebase structure (SKILL.md). * Sanitization: No sanitization or escaping of the ingested code content is performed before processing.
Audit Metadata