ClawHub
Back to skill

Security audit

Ops Dashboard

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides a local workspace health report and does not show hidden network access, persistence, destructive behavior, or credential handling.

Install only if you are comfortable with the agent reading local repository health information, including git status, recent commits, disk usage, load averages, and directory sizes. Avoid pointing --workspace at sensitive folders unless you intend that metadata to be included in the report.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises and invokes a Python CLI that inspects workspace state, repository metadata, and system information, but the manifest does not declare any tool scope or permissions boundaries. That omission can cause the agent to use shell and file-read capabilities without explicit user-facing constraints, increasing the chance of unintended data exposure from arbitrary workspaces or repositories.

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/ops_dashboard.py (reported line 32)May include surrounding context.

python
def get_git_status(workspace: Path) -> str:
    try:
        result = subprocess.run(
            ["git", "-C", str(workspace), "status", "-sb"],
            capture_output=True,
            text=True,

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/ops_dashboard.py (reported line 45)May include surrounding context.

python
def get_recent_commits(workspace: Path, count: int = 3) -> List[str]:
    try:
        result = subprocess.run(
            ["git", "-C", str(workspace), "log", "-n", str(count), "--oneline"],
            capture_output=True,
            text=True,

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 · tests/test_ops_dashboard.py (reported line 11)May include surrounding context.

python
def run_cli(args, workspace):
    return subprocess.run(
        [sys.executable, str(SCRIPT_PATH)] + args,
        capture_output=True,
        text=True,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill description explains what metrics are collected, but it does not clearly warn users that running the skill inspects repository metadata, recent commits, directory sizes, and broader system/workspace state. This lack of an explicit privacy and inspection notice can lead users to run it without understanding that potentially sensitive operational and developer information will be surfaced.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction to use the skill whenever you need to check health before deployments, push updates, or help teammates with a slow workspace is fairly broad and does not define clear boundaries for when the skill should or should not be invoked. Because this is a markdown file, vague invocation guidance can increase unintended activation in routine conversations about deployments or support.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.