ClawHub
Back to skill

Security audit

Token Tamer — AI API Cost Control

Security checks across malware telemetry and agentic risk

Overview

Token Tamer is a local, user-directed cost-tracking tool that writes API usage records to a configurable JSON file and does not show hidden network, credential, or privileged behavior.

Install only if you are comfortable running local Python scripts from this publisher. Set the usage JSON path to a private location, restrict file permissions, avoid putting prompts, secrets, customer identifiers, or regulated data in task/session/metadata fields, and be cautious when emailing or sharing reports because they may reveal provider usage and business activity.

SkillSpector

By NVIDIA
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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill demonstrates capabilities to read and write local files and may interact with external providers, but it does not declare any permissions or trust boundaries. This mismatch can cause the hosting agent or user to approve and run the skill without understanding that it can modify local usage records or make network-dependent operations, which weakens security review and least-privilege controls.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README explicitly advertises logging every API call and persistent JSON storage, but it does not clearly disclose what sensitive fields may be retained or warn users about privacy and data-handling implications. In a cost-tracking skill, task names, session identifiers, model metadata, and potentially prompt-derived context can expose sensitive operational or business information if stored insecurely or retained longer than expected.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The code persists each usage record to disk, including an arbitrary metadata dictionary, without any filtering, minimization, or notice to the user. In a cost-tracking skill, that metadata can easily contain prompts, identifiers, API payload fragments, or other sensitive operational data, creating an unintended local data-retention/privacy risk if callers pass secrets or personal data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.