ClawHub
Back to skill

Security audit

Thermometer

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a scoped performance-testing workflow with explicit approval safeguards and no hidden installation or background activity.

Use a scoped test workload and review benchmark commands before running them against production systems. Expect code edits and retained profiling results. The companion check skill and repository lint script require separate review if used.

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 131)May include surrounding context.

md
- the workload cannot be reproduced consistently
- profiler overhead or environmental noise exceeds the expected gain
- the measured bottleneck is an unavailable external service
- the proposed change alters correctness, security, or a public contract without approval
- a second optimization requires a different workload or hypothesis

## Common mistakes

Static analysis

No suspicious patterns detected.