ClawHub
Back to skill

Security audit

Policy Lawyer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed policy lookup helper that reads user-selected policy documents and does not show hidden execution, persistence, or exfiltration behavior.

Before installing, understand that the CLI can read whichever policy file path you provide with --policy-file, so only point it at documents you intend the agent to inspect. The skill otherwise appears to be a read-only helper for policy lookup.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
91% confidence
Finding
The skill documentation advertises shell execution and file-reading behavior through a CLI, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization ambiguity where an agent may invoke broader local file access or shell capabilities than a reviewer expects, especially because `--policy-file` allows reading arbitrary paths, including from other workspaces.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run_cli(args):
    return subprocess.run(
        [sys.executable, str(SCRIPT_PATH)] + args,
        capture_output=True,
        text=True,
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Static analysis

No suspicious patterns detected.