adhx

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch and consume arbitrary public X/Twitter posts via the ADHX API (e.g., "curl -s https://adhx.com/api/share/tweet/{username}/{statusId}" in the Workflow and Examples), which ingests untrusted user-generated content that the agent then reads and uses to drive summaries/analyses and potentially further actions.