ClawHub
Back to skill

Security audit

User Insight Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed user-research coaching skill with no executable code, persistence, credential use, or hidden system access.

This skill appears safe to install as a coaching and analysis aid. Treat its external links and research framework as references, and avoid giving any agent broad access to analytics, recordings, or customer data unless you intentionally authorize that access in a separate task.

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 100)May include surrounding context.

md
## Red Flags

- Behavioral and survey data presented together without checking for Surface–Behavioral conflicts
- "User research" = interviews only; no behavioral layer
- No Deep Layer evidence ever collected for this behavior
- Interventions designed before a driver has been identified

Static analysis

No suspicious patterns detected.