Scan a skill for malicious patterns

Statically scan a SKILL.md string (markdown) or structured manifest (frontmatter + body) and return a two-tier verdict (warning when suspected malicious, error when high-confidence malicious). Does not persist or gate.

Authentication

AuthorizationBearer
API key or Clerk session token

Request

This endpoint expects a map from strings to any.

Response

Scan verdict

Errors

400
Bad Request Error
401
Unauthorized Error
403
Forbidden Error