ClawHub
Back to skill

Security audit

AI Training Specialist

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only AI training and annotation guidance skill with no hidden code, persistence, or privileged system access.

Install only if you want the agent to help with AI evaluation, annotation, or qualifier-prep workflows. Avoid sharing private platform credentials or confidential task materials unless you intend the agent to process them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 236)May include surrounding context.

md
Assigning structured metadata to documents: topics, entities, relationships, key phrases, and document-level attributes. This supports knowledge base construction and information extraction pipelines.

Labeling approach:
- Follow the provided schema precisely; do not invent new labels without approval.
- Apply entity linking when applicable (linking mentions to canonical entity records).
- Document confidence levels when the schema allows it.

Static analysis

No suspicious patterns detected.