recipe-front-design
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted user data.
- Ingestion points: User requirements are ingested via the
$ARGUMENTSvariable inSKILL.mdand passed to therequirement-analyzersub-agent. Additionally, the skill requests a file path for prototype code from the user in Step 2. - Boundary markers: The skill does not utilize explicit boundary markers or isolation instructions when interpolating user-provided requirements into sub-agent prompts.
- Capability inventory: The skill invokes several sub-agents (
requirement-analyzer,ui-spec-designer,technical-designer-frontend, etc.) which have the capability to analyze codebases and write design documentation to the file system. - Sanitization: No explicit sanitization or validation logic is present for the ingested requirements or prototype paths.
- Risk Mitigation: The potential impact is significantly reduced by the implementation of mandatory
[STOP]markers throughout the execution flow, ensuring that a human must review and approve the output of each sub-agent (e.g., requirement analysis, UI specs, and design documents) before the process continues.
Audit Metadata