Back to skill

Security audit

Test Skill from TPClawHub

Security checks for vulnerabilities and agentic risk

Overview

This is a minimal test skill with no bundled executable code, but its install example should be treated cautiously because it uses an unpinned npx command.

Before installing, verify the ClawHub CLI source and publisher, prefer a pinned reviewed version instead of a floating `npx` command, and avoid running it with sensitive environment variables such as API keys unless you know why they are needed.

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:27
Finding

Unpinned Third-Party Package Execution Through npx

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 27-30
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

Complete Code Snippet:

markdown
Here is an example of how to use this skill:

```bash
npx clawhub install test-skill-from-tpclawhub
text

### Technical Analysis

The documented command invokes `clawhub` through `npx` without specifying a package version or integrity constraint. If the package is not already available locally, `npx` may retrieve the current package release from the configured npm registry and execute its code with the invoking user's privileges.

Because the effective package contents can change after this skill has been reviewed, users cannot determine from the repository alone what code will execute. The project contains no lockfile, package manifest, integrity hash, verified local implementation, or trusted version constraint for the referenced CLI.

This is a supply-chain weakness rather than evidence that the current `clawhub` package is malicious.

### Attack Path

1. An attacker compromises the npm account, package publication process, registry resolution path, or a future release of the referenced `clawhub` package.
2. The attacker publishes a modified package version containing malicious installation or runtime behavior.
3. A user follows the documented `npx clawhub install test-skill-from-tpclawhub` command.
4. `npx` resolves and downloads the attacker-controlled package version when no trusted local version is available.
5. The malicious package executes under the user's account and inherits the command's environment and accessible resources.

### Impact Assessment

Successful exploitation could provide code execution with the privileges of the user running the command. Depending on that user's permissions and environment, the package could access readable files, environment variables, developer credentials, source repositorie
...[truncated 439 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the CLI to a reviewed, trusted version rather than allowing implicit resolution of the latest release, for example:
    bash
    npx --yes clawhub@<reviewed-version> install test-skill-from-tpclawhub
    
  2. Document the package's official publisher, registry, and source repository so users can verify package provenance.
  3. Prefer installing the CLI as a declared project dependency with a committed lockfile and then invoking the locked local binary.
  4. Where supported, verify registry integrity metadata, package signatures, provenance attestations, or published checksums before execution.
  5. Run package-management commands with least privilege and without unnecessary secrets in the environment.
  6. Add explicit dependency and installation documentation; the current references to “required dependencies” and a “main script” do not identify any corresponding project files.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (2)

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
Set the following environment variables:

- `API_KEY`: Your API key
- `DEBUG`: Enable debug mode (optional)

## Examples

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The documentation instructs users to run npx clawhub install test-skill-from-tpclawhub without pinning an exact package version. This can cause users to execute whatever version is current at install time, increasing supply-chain risk if a malicious or compromised update is published later.

Content

No source excerpt is available for this finding.