kiro-validate-design

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill performs legitimate analysis of technical documents and codebase patterns.
  • [COMMAND_EXECUTION]: The skill uses local search tools (grep) to gather architectural context from the codebase. This behavior is restricted to the local environment and is necessary for its stated purpose.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes project documents and codebase content that could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Reads files from .kiro/specs/, product.md, tech.md, structure.md, and arbitrary files in the codebase via grep.
  • Boundary markers: No explicit markers or 'ignore' instructions are used when interpolating file contents into the prompt.
  • Capability inventory: Limited to reading local files and searching the codebase; no network access or system-level modification capabilities are requested.
  • Sanitization: No validation or sanitization is performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:15 AM
Security Audit — agent-trust-hub — kiro-validate-design