hackathon-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples of passing API keys directly on the command line (oatmeal login --api-key ...) and shows a secret-like placeholder (sk_live_...), which encourages embedding secrets verbatim in generated commands/outputs and thus poses a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly exposes public, user-generated content via the "Public Browsing (no auth required)" commands (e.g., "oatmeal browse submissions ", "oatmeal browse hackathons", "oatmeal browse results "), which the agent is expected to read and could materially influence subsequent CLI actions, creating a risk of indirect prompt injection.