Security audit
tokenjuice
Security checks for vulnerabilities and agentic risk
Overview
ClawScan rates the tokenjuice plugin benign, with all reviewed dimensions marked ok and no findings reported by the completed scanner.
The available scan results support a benign verdict and report no findings. Benign does not mean risk-free, and the scanner results alone do not guarantee safety; consider whether the plugin suits your needs and use your usual care when installing.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
SkillSpector was not run because this plugin release contains no bundled skills.
Endor dependency reachability
Checked Nov 16, 2026 · 2:35 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
