rootdata

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

• Third-party content exposure detected (high risk: 0.80). The skill makes runtime POST requests to the public RootData API (https://api.rootdata.com/open/skill) as shown in exports.py and SKILL.md to fetch project descriptions, social_media, funding rounds and job-change data — untrusted public content that the agent is expected to read and use for research, which could materially influence its actions.