giggle-generation-speech

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls giggle.pro endpoints (see scripts/text_to_audio_api.py: BASE_URL https://giggle.pro, e.g., /api/v1/project/preset_tones and /api/v1/generation/task/query) and SKILL.md/Cron instructions require the agent to read and act on the script's stdout (forward raw plain-text, interpret JSON status to continue/stop polling), so untrusted third-party responses can directly influence tool use and workflow decisions.