backend-architect-lite
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to provide high-level architectural recommendations and includes specific security gates for authentication (OAuth, OIDC, PKCE) and authorization (RBAC, ABAC).
- [PROMPT_INJECTION]: The skill implements defensive instructions by explicitly warning the agent to treat MCP tools, A2A agents, and model outputs as untrusted external boundaries that require validation and audit, which mitigates indirect prompt injection risks.
- [CREDENTIALS_UNSAFE]: The skill promotes secure credential management by instructing the agent to keep secrets out of logs and runtime environment files (.env).
- [DATA_EXFILTRATION]: No network exfiltration patterns or unauthorized data access commands were detected. The skill's focus is on text-based architectural guidance.
Audit Metadata