gstack

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

• Third-party content exposure detected (high risk: 0.90). gstack's SKILL.md explicitly instructs the agent to navigate arbitrary external URLs (e.g., $B goto <url> in the "QA Workflows" and "Navigation" sections) and to run reading/JS commands (text, html, js, snapshot, etc.) whose outputs are used to decide and drive follow-up actions (click/fill/assert), so untrusted third‑party page content can materially influence subsequent tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The setup instructions include a runtime command that fetches and executes remote code via "curl -fsSL https://bun.sh/install | bash" (used if bun is not installed during the skill setup), which directly runs third-party code as a required dependency.