model-council
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's scripts (notably scripts/api_council.py) call external model APIs and CLIs (Anthropic/OpenAI/Google/xAI endpoints and detected CLI tools) and then collect and synthesize those providers' responses as part of the workflow, meaning it ingests untrusted third‑party output that could carry indirect prompt injection.
Audit Metadata