inworld

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch documentation from https://www.pixazo.ai/models/inworld.md when needed, which constitutes reading external web content (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external documentation (https://www.pixazo.ai/models/inworld.md) to load runtime parameter schemas and instructions, but the publisher provenance of this third-party API gateway is unknown/unverified, making it a high-risk operational dependency.