qa-explorer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's bundled scripts example explicitly shows passing an auth cookie as a CLI argument (--auth-cookie <cookie>), which can require the agent to embed secret cookie values verbatim into generated commands or code, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Mode 2 (Post-Dev) explicitly opens and explores arbitrary user-provided URLs (see SKILL.md and references/mode-postdev.md) and the bundled scripts (scripts/inventory.js and scripts/happy-path.js) crawl pages, extract visible text, form fields, messages and navigation, and then use those extracted contents to generate test cases and drive further actions, meaning untrusted third‑party page content is ingested and can materially influence the agent's behavior.