ClawHub
Back to skill

Security audit

Openclaw Skill Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed scanner wrapper for OpenClaw skills, with user-directed install and quarantine actions and no evidence of hidden execution, exfiltration, or persistence.

Install only if you are comfortable running local shell wrappers that scan, copy, and sometimes move OpenClaw skill directories. Review and trust the separate `cisco-ai-defense/skill-scanner` checkout, the OpenClaw CLI used for `--catalog`, and the npm-resolved `clawhub` package before using the staging installer or any optional watcher setup.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code’s actual function is inventory/discovery of skill directories from filesystem locations and, when requested, via the OpenClaw CLI catalog. It validates paths, rejects symlinked skill directories/manifests, traverses roots, and emits discovered local paths. There is no logic for analyzing skill contents for security issues, generating findings with severity levels, or quarantining any skills. While the symlink checks are security-relevant hardening, they are only supporting validation for discovery and do not constitute the declared scanner/quarantine behavior. Therefore the declared description materially misrepresents the primary purpose and capabilities of this code chunk.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
Grouped skills are discovered up to six levels deep, stopping at `SKILL.md`.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The script executes npx -y clawhub without pinning an exact package version, so it may fetch and run whatever version the registry resolves at install time. Because this script is part of a security-sensitive install/scan workflow, a compromised, malicious, or unexpectedly changed upstream clawhub release could execute arbitrary code before the local safety scan occurs, undermining the trust boundary.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/discover_skill_dirs.py (reported line 18)May include surrounding context.

python
def cli_json(command: list[str]) -> dict:
    result = subprocess.run(command, capture_output=True, text=True, timeout=30)
    if result.returncode:
        raise ValueError('OpenClaw catalog command failed; no complete inventory is available')
    data = json.loads(result.stdout)

Static analysis

No suspicious patterns detected.