ClawHub
Back to skill

Security audit

Token Saver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent Claude cost-reporting helper that uses your Anthropic API key only for Anthropic usage stats and asks before changing local config.

Before installing, understand that the skill can use your Anthropic API key to query Anthropic usage data and may inspect local OpenClaw prompt/config files for cost analysis. Only approve proposed edits after reviewing the shown diff.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill uses sensitive capabilities—environment access to read ANTHROPIC_API_KEY and network access via curl—but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an over-broad execution model where the runtime may permit more access than reviewers or users expect, weakening least-privilege controls and making future prompt or skill changes riskier.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
def fetch_usage(api_key, days=7):
    """Fetch usage stats from Anthropic API."""
    url = f"https://api.anthropic.com/v1/usage?days={days}"
    req = urllib.request.Request(
        url,
        headers={

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/token_report.py (reported line 46)May include surrounding context.

python
def fetch_usage(api_key, days=7):
    """Fetch usage stats from Anthropic API."""
    url = f"https://api.anthropic.com/v1/usage?days={days}"
    req = urllib.request.Request(
        url,
        headers={

Static analysis

No suspicious patterns detected.