ClawHub
Back to skill

Security audit

model-usage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local cost-summary helper for CodexBar logs, with no evidence of hidden behavior, exfiltration, or destructive actions.

Install only if you are comfortable letting CodexBar read local Codex or Claude usage logs to compute cost summaries, and review the third-party CodexBar Homebrew package because the live mode depends on that external CLI.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs users to run a bundled Python script and invokes external commands (python, codexbar, shell pipelines, file/stdin input), but it does not declare any tool scope such as permissions or allowed-tools. That creates a mismatch between documented capabilities and declared restrictions, making it easier for an agent runtime to grant broader-than-intended shell or file access without explicit review.

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/model_usage.py (reported line 37)May include surrounding context.

python
def run_codexbar_cost(provider: str) -> List[Dict[str, Any]]:
    cmd = ["codexbar", "cost", "--format", "json", "--provider", provider]
    try:
        output = subprocess.check_output(cmd, text=True)
    except FileNotFoundError:
        raise RuntimeError("codexbar not found on PATH. Install CodexBar CLI first.")
    except subprocess.CalledProcessError as exc:

Static analysis

No suspicious patterns detected.