ClawHub
Back to skill

Security audit

learning-system

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not malicious, but it should be reviewed because it directs ongoing collection and cross-project reuse of task, user feedback, collaborator, and project metadata without clear privacy or retention limits.

Review this before installing if your projects contain private code, customer data, sensitive operational history, or identifiable collaborator information. Use it only with clear local rules for what may be recorded, how long learning records are kept, whether git diffs may be included, and whether insights can be reused across projects.

A.I.G

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

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata uses broad activation terms like performance learning, knowledge accumulation, system evolution, system overview, and tracked metrics, which can cause the skill to be invoked in loosely related contexts. Over-broad routing increases the chance that sensitive operational or user data is pulled into this skill unnecessarily, expanding exposure and enabling inappropriate data collection or recommendations outside its intended scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes collecting detailed task observations, user feedback, collaborator identities, timing, and contextual project data, but provides no privacy, retention, minimization, consent, or access-control guidance. In practice this can lead to persistent storage of sensitive operational metadata or personal information, creating privacy leakage, profiling risks, and accidental cross-project disclosure through the learning system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.