ClawHub
Back to skill

Security audit

skill-gardener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local skill-maintenance workflow with bounded validation tooling and no hidden network, persistence, or exfiltration behavior found.

Install only if you want an agent to help maintain local skills. Because it can edit skill files when authorized, review proposed diffs and keep its scope to user-owned skill roots and sanitized evidence.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
This is a clear mismatch because the declared purpose is about generating or repairing skills from workflows, while the code performs only static, read-only validation of existing skill directories. It does not create, modify, repair, or save skills at all. Its primary purpose is materially different: auditing structure and metadata integrity of skill files on the local filesystem.

Scope Creep

Low
Category
Excessive Agency
Content
issue(path, "allowed-tools must be a non-empty string or list of non-empty strings when provided")
        if isinstance(fields.get("compatibility"), str) and len(fields["compatibility"]) > 500:
            issue(path, "compatibility exceeds 500 characters")
        # OpenClaw accepts nested metadata; it is not limited to flat strings.
        if "metadata" in fields and fields["metadata"] is not None and not isinstance(fields["metadata"], dict):
            issue(path, "metadata must be a mapping when provided")
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.