ClawHub
Back to skill

Security audit

OpenClaw Contributor

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed OpenClaw contribution guidance and helper scripts, with no evidence of hidden persistence, credential access, remote payloads, or destructive behavior.

Install this only if you want an agent to help with OpenClaw repository contributions. Expect it to run git and project validation commands in the target checkout and optionally create a PR body file when requested; review generated PR text and commands before publishing or running expensive checks.

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 (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
- Run `scripts/recommend_checks.py --repo <openclaw-repo>`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
- Run `scripts/recommend_checks.py --repo <openclaw-repo>`.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
- Run `scripts/recommend_checks.py --repo <openclaw-repo>`.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs the agent to run local scripts and validation commands and to edit repository content, which implies shell execution and file modification capabilities. Because the skill does not declare any explicit tool scope such as allowed-tools or permissions, an agent may perform broader actions than a reviewer expects, increasing the risk of unintended command execution or repository changes if the skill is invoked in an untrusted or sensitive environment.

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/generate_pr_body.py (reported line 13)May include surrounding context.

python
def run(cmd):
    result = subprocess.run(cmd, text=True, capture_output=True)
    if result.returncode != 0:
        raise RuntimeError(result.stderr.strip() or result.stdout.strip() or f'command failed: {cmd}')
    return result.stdout

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/recommend_checks.py (reported line 10)May include surrounding context.

python
def run(cmd, cwd):
    result = subprocess.run(cmd, cwd=cwd, text=True, capture_output=True)
    if result.returncode != 0:
        raise RuntimeError(f"command failed ({' '.join(cmd)}): {result.stderr.strip() or result.stdout.strip()}")
    return result.stdout

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/recommend_checks.py (reported line 23)May include surrounding context.

python
def detect_default_base(repo: Path) -> str:
    for candidate in ("upstream/main", "origin/main", "main"):
        result = subprocess.run(["git", "rev-parse", "--verify", candidate], cwd=repo, text=True, capture_output=True)
        if result.returncode == 0:
            return candidate
    return "main"

Static analysis

No suspicious patterns detected.