office-hours

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to include the founder's "verbatim" answers in the generated brief, so if a user pastes API keys, tokens, or passwords into their answers the LLM will echo those secrets exactly, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The skill /cs:office-hours <topic> ingests outsider-provided free text from the user (founder answers six questions in writing) to generate a brief before routing to other roles, making the workflow directly driven by free-form input.