steward

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read an API key from a local configuration file and include it verbatim in the Authorization header of curl commands.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The steward skill reads tickets, pulls, and comments from the customer's catalyst-cloud tenant API endpoints, exposing the agent to outsider-authored free text.