Security audit
MrScraper
Security checks for vulnerabilities and agentic risk
Overview
ClawScan classified the mrscraper plugin as benign, with no findings reported by the completed scan; several assessment areas remain notes, so the evidence is not conclusive.
The verdict is benign, not a guarantee of safety. The available scanner results report no findings, but provide limited detail about the plugin and leave several assessment areas at note; consider whether its purpose and installation requirements fit your needs before 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 findings are pending for this release.
Endor dependency reachability
Checked Nov 22, 2026 · 6:19 AM UTC
Scan failed: Endor analysis failed. Request a rescan to try again.
