generate-tests

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read credentials from project memory and write them verbatim into a generated .env.test.local (and to produce auth artifacts containing session cookies), which requires the LLM to handle and output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow reads outsider-authored free text from ~/.claude/skills/app-navigator/app-map.md and ~/.claude/skills/app-navigator/playbooks/*.md (app-navigator outputs and playbooks), then uses that content to generate Playwright test code that is fed into the agent’s LLM context during generation.