java-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive local paths (such as SSH keys) are accessed. The skill only interacts with project-specific documentation.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external code or scripts are included; the skill relies entirely on markdown-based instructions and built-in AI capabilities.
- [Indirect Prompt Injection] (SAFE): The skill processes untrusted project documentation, which is a potential ingestion surface. However, the risk is negligible due to the lack of execution capabilities. Ingestion points: Files like architecture_decisions.md via memoryStore; Boundary markers: Absent; Capability inventory: No code execution, network access, or system-level writing; Sanitization: Absent.
- [Persistence Mechanisms] (SAFE): No attempts to modify system startup files or schedule recurring tasks.
Audit Metadata