design-audit
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and templates reveals no malicious intent, obfuscation, or unauthorized access patterns. The skill is designed to provide design advice and structured plans, which are then subject to human review and execution by a separate agent.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external project files and live application data, though the risk is negligible due to the absence of exploitable tools.\n
- Ingestion points: Reads project-specific files like
PRD.md,APP_FLOW.md, andTECH_STACK.md(SKILL.md, lines 19-27).\n - Boundary markers: No explicit delimiters are used to wrap ingested content or prevent the agent from following instructions embedded within those files.\n
- Capability inventory: The skill has no capabilities for file-write operations, subprocess spawning (exec/eval), or network access; its output is restricted to text-based audit reports.\n
- Sanitization: No sanitization or validation is performed on the data ingested from project files before it is used in the reasoning process.
Audit Metadata