ai-agents-architect
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No patterns of instruction override, jailbreaking, or system prompt extraction were found. The skill uses standard grounding instructions to ensure behavior remains within the provided reference context.
- Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or network operations are present. The skill does not access external resources.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not reference or install any external packages (npm/pip) or execute remote scripts.
- Obfuscation (SAFE): All content is in plain text markdown. No Base64, zero-width characters, or homoglyph attacks were detected.
- Indirect Prompt Injection (SAFE): While the skill is designed to review and validate user input/code, it lacks any side-effect capabilities (such as file-writing or command execution) that could be exploited via injection. The capability tier is 'INFO/Display only'.
Audit Metadata