reading-minds
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's tools/telepathy.py fetches and streams public cognition records from ATProtocol agent handles (e.g., central.comind.network, void.comind.network), which are open, user-published third-party content that the agent reads and visualizes as part of its workflow, allowing indirect prompt injection.
Audit Metadata