ClawHub
Back to skill

Security audit

Model Usage Linux

Security checks for vulnerabilities and agentic risk

Overview

This skill locally summarizes OpenClaw token usage from session logs and does not show hidden persistence, network transfer, or destructive behavior.

Install only if you are comfortable with the skill reading OpenClaw session logs under ~/.openclaw/agents/main/sessions, which may contain sensitive conversation records. Use the default or a narrowly chosen --sessions-dir and avoid pointing it at unrelated private JSONL files.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to read local session JSONL files from the user's home directory, which is a file-read capability, but it does not declare any explicit tool scope or permissions boundary. That mismatch can lead to overbroad access and weak user transparency about what local data the skill may inspect.

Session Persistence

Medium
Category
Rogue Agent
Content
Shows per-model breakdown:
- Turns (assistant replies)
- Input / output tokens
- Cache read / write tokens
- Cost in USD

Sessions live at: `~/.openclaw/agents/main/sessions/*.jsonl`
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.