human-ai-system-builder

Warn

Audited by Snyk on Jul 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). AGENTS.md mandates running compose-agentsmd (including via npx) at session start and agent-ruleset.json / AGENTS.md reference github:metyatech/agent-rules (github:metyatech/agent-rules and github:metyatech/agent-rules@HEAD/rules/domains/skill/repository.md), which are fetched at runtime to regenerate rules that directly control agent instructions, so the remote git source is a runtime dependency controlling prompts.

Issues (1)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 23, 2026, 07:52 AM
Issues
1
Security Audit — snyk — human-ai-system-builder