Back to skill

Security audit

Tokenguard Pro

Security checks for vulnerabilities and agentic risk

Overview

TokenGuard Pro has a plausible cost-analysis purpose, but its package is incomplete and asks users to install/run a log-analyzing command whose implementation is not present for review.

Review this package carefully before installing. Its purpose is understandable, but install only from a verified, pinned ClawHub installer and do not run it on OpenClaw logs containing secrets or private data until the missing `tokenguard-analyze` implementation and clear local data-handling guarantees are available.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:32
Finding
Unpinned Package Execution During Installation## Vulnerability Details **File Location**: `SKILL.md:32-36`; duplicated in `README.md:24-28` **Vulnerability Type**: Unpinned third-party package execution **Risk Level**: Medium ### Vulnerable Code `SKILL.md:32-36`: ```bash ## Installation ```bash npx clawhub install tokenguard-pro ``` ``` `README.md:24-28`: ```bash ## Installation ```bash npx clawhub install tokenguard-pro ``` ``` ### Technical Analysis The documented installation procedure invokes `clawhub` through `npx` without specifying a package version or verifying its integrity. If the package is not already available locally, `npx` can retrieve the current package release from the configured npm registry and execute it immediately. Because neither an exact version nor an integrity hash is supplied, the code executed by this command may differ from the code that existed when the Skill was audited. This creates a supply-chain trust dependency on the npm package, registry configuration, publisher account, and all transitive components used by the retrieved package. The artifact also contains no lockfile or other mechanism that would make this installation command reproducible. This finding does not establish that the current `clawhub` package is malicious; it identifies an unsafe, mutable execution path that could become exploitable following package compromise, malicious publication, dependency confusion, or registry redirection. Additionally, the supplied artifact does not contain the `tokenguard-analyze` executable referenced by `package.json` and `clawhub.yaml`. Therefore, its advertised runtime behavior could not be audited from the provided files. This missing file is an audit limitation rather than evidence that malicious code exists. ### Attack Path 1. An attacker compromises the publisher account, registry package, package dependency chain, or the user's npm registry configuration. 2. The attacker publishes or serves a modified `c ...[truncated 1196 chars]
Remediation
## Remediation Suggestions 1. Pin the installer to a specifically reviewed release: ```bash npx --yes clawhub@X.Y.Z install tokenguard-pro ``` 2. Document the expected official npm registry and package publisher so users can verify package provenance before execution. 3. Publish and document an expected package integrity digest or signed release artifact. 4. Prefer a verified, locally installed installer over an implicit download-and-execute workflow. 5. Use lockfiles and exact versions for all development and installation dependencies where applicable. 6. Advise users to run installation with a non-privileged account and not to use `sudo`. 7. Add the missing `tokenguard-analyze` executable to the reviewed package so the installed behavior can be inspected before release. 8. Ensure `package.json`, `clawhub.yaml`, and the distributed archive contain the same reviewed files and versions.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding
The README instructs users to run `npx clawhub install tokenguard-pro` without pinning a specific package version. That allows whatever version is current at execution time to be fetched and run, increasing supply-chain risk if the package is compromised, replaced, or unexpectedly changed. In a skill-installation context, this is more dangerous because users are likely to copy-paste the command directly from documentation.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states that the tool analyzes session logs, tool call sequences, model usage, and context growth, but it does not warn users that these inputs may contain sensitive prompts, secrets, personal data, or business information. This omission can lead users to expose privacy-sensitive data to the tool or to store/export reports insecurely, especially since the skill is explicitly aimed at reviewing historical agent activity at scale.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill repeatedly states it scans session logs and requires access to OpenClaw logs, but it does not warn users that those logs may contain sensitive prompts, credentials, personal data, or proprietary context. In a log-analysis skill, this omission is security-relevant because users may enable analysis on data they would otherwise sanitize, export, or restrict.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding
The installation command uses `npx clawhub` without pinning a specific version, so users may fetch and execute whatever version is current at install time. This creates a supply-chain risk: a compromised publisher account, malicious update, or unexpected breaking release could result in unreviewed code execution on the user's system.

Static analysis

No suspicious patterns detected.