Back to skill

Security audit

Cobrain – Shared memory for all your AIs

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because its broad activation around notes and memory may lead to conversation content being saved remotely without clear, task-specific consent.

Before installing, consider whether you want a skill that may save conversation content to remote memory after broad triggers. The scan was partial because some referenced paths were missing, so the evidence is incomplete; the verdict is suspicious, not a claim that the author acted maliciously.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Activation includes ordinary references to notes, memory, and decisions without requiring Cobrain context.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The activation description includes generic references to notes or memory and anything considered worth keeping, without requiring an explicit Cobrain request or established user preference. Combined with instructions to save information immediately, this can cause unrelated or sensitive conversation content to be persisted to a remote service and made available to other connected AIs without task-specific authorization. Persistent memory is the skill's legitimate purpose, which reduces suspicion of malicious intent, but does not establish consent to save arbitrary conversation content.

Content

No source excerpt is available for this finding.