ClawHub
Back to skill

Security audit

Clawhub Release Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a release-auditing helper that runs local validation and ClawHub inspection commands with disclosed, user-directed publishing steps.

Install this only if you intend to let your agent inspect local skill folders and run ClawHub/OpenClaw release commands. Review the exact skill path, version, warnings, and any publish command before confirming, because publishing changes public release state even though the skill requires confirmation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill claims strong validation, packaging, publish verification, dependency comparison, and failure diagnosis capabilities, but the finding indicates the implemented behavior may not actually perform those checks. In a release-auditing context, this can create a false sense of assurance, causing users to publish unverified or misconfigured skills while believing required security and integrity checks were completed.

Content

No source excerpt is available for this finding.

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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/checklist.md (reported line 24)May include surrounding context.

md
- Many rapid versions usually mean the process is broken, not just evolving.
- Validation errors outrank memory of the docs.
- Scan mismatches usually come from declaration drift, not random platform bugs.
- Never tell the user a command worked without checking the output.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · references/checklist.md (reported line 24)May include surrounding context.

md
- Many rapid versions usually mean the process is broken, not just evolving.
- Validation errors outrank memory of the docs.
- Scan mismatches usually come from declaration drift, not random platform bugs.
- Never tell the user a command worked without checking the output.

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/analyze_history.py (reported line 19)May include surrounding context.

python
def run(cmd):
    p = subprocess.run(cmd, capture_output=True, text=True)
    return p.returncode, (p.stdout + p.stderr).strip()

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/failure_buckets.py (reported line 11)May include surrounding context.

python
def run(cmd):
    p = subprocess.run(cmd, capture_output=True, text=True)
    return p.returncode, (p.stdout + p.stderr).strip()

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/release_worthiness.py (reported line 15)May include surrounding context.

python
def run(cmd):
    p = subprocess.run(cmd, capture_output=True, text=True)
    return p.returncode, (p.stdout + p.stderr).strip()

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/preflight.py (reported line 124)May include surrounding context.

python
def run(cmd):
    proc = subprocess.run(cmd, capture_output=True, text=True)
    return proc.returncode, (proc.stdout + proc.stderr).strip()

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/verify_publish.py (reported line 12)May include surrounding context.

python
def run(cmd):
    proc = subprocess.run(cmd, capture_output=True, text=True)
    return proc.returncode, (proc.stdout + proc.stderr).strip()

Static analysis

No suspicious patterns detected.