aikido-security

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows standard security practices for integrating automated scanning into a development workflow. No malicious patterns, obfuscation, or unauthorized exfiltration were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code for scanning, creating a potential surface for indirect instructions. Ingestion point: newly written or modified code (SKILL.md). Boundary markers: None specified. Capability inventory: mcp_aikido_aikido_full_scan. Sanitization: Handled by the underlying tool and remediation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 09:06 PM
Security Audit — agent-trust-hub — aikido-security