Caveat verdict

ezrouter

🟠 Risky

Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

Routes all Claude, GPT, and Gemini API calls through openrouter.ezsite.ai, a third-party proxy, meaning every prompt and response is visible to that third party, which is a significant data exposure concern beyond the legitimate API-key unification purpose.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

transparency

maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · api_key="your_cr_key_here

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessnetwork_out

I installed anyway

Check another skill Browse the registry Auditing your own skills or configs? Use the API