cs-build-plan-app

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs the agent to read and print values from a local .codespring/config.json (including a direct cat of that file), which could expose API tokens or other secrets verbatim in the agent's output.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow “plan an app from an idea” ingests outsider-authored free text from the user’s supplied call/transcript/notes/screenshots and keeps verbatim phrasing to generate the plan (phases A/GATE onward).