recipe-design
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted user data into its operational flow.
- Ingestion points: User-provided requirements are ingested through the
$ARGUMENTSvariable in theSKILL.mdfile. - Boundary markers: The skill does not implement delimiters (like triple quotes) or specific instructions for the agent to ignore embedded commands within the requirement input.
- Capability inventory: The skill orchestrates multiple sub-agents—including
requirement-analyzer,codebase-analyzer,technical-designer,code-verifier,document-reviewer, anddesign-sync—which collectively possess the capability to read project source code and write design documentation (as defined inSKILL.md). - Sanitization: No sanitization, filtering, or validation logic is defined to check the contents of the requirements input before it is passed to the sub-agents.
Audit Metadata