Caveat verdict

.mcp.json

design-researh

🟠 Risky

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

MCP server config spawns local processes

The skill has broad capabilities such as 'mcp_server_config' and 'env_access_declared', which could potentially be misused. However, the content seems to be focused on a legitimate purpose of performing design research.

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

100

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

MCP server config spawns local processes — commands run with user privileges

LLM06 · ASI02 · ASI03

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: BRAVE_API_KEY). Requires 1 system binary.

mcp_server_configprocess_execenv_access_declared

I installed anyway

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