Back to skill

Security audit

Clawhub Publishing Workflow

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a publishing guide, but it explicitly recommends stealth browser and residential proxy tactics to get around authentication bot checks.

Review this skill carefully before installing. The publishing and token-login steps are straightforward, but avoid the stealth browser and residential proxy guidance unless ClawHub and the relevant providers explicitly authorize that use; prefer documented token authentication or official support. Consider pinning and verifying the ClawHub CLI package before global installation.

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 (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:24
Finding

Unpinned Global Installation of a Third-Party CLI Package

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 24–27
Vulnerability Type: Unpinned third-party dependency installed globally
Risk Level: Medium

Vulnerable Code:

bash
1. **ClawHub CLI installed:**
   ```bash
   npm install -g clawhub
   ```

Technical Analysis

The workflow directs users to install the latest available version of the clawhub npm package globally. It does not pin a reviewed version, verify package integrity, identify an expected publisher, or otherwise constrain the retrieved artifact.

npm installations may execute package lifecycle scripts with the permissions of the invoking user. Because -g installs the package globally, a malicious or compromised package release could affect the user's broader development environment rather than an isolated project directory. The effective package contents may also change after this Skill has been reviewed.

This finding does not establish that the current clawhub package is malicious. The risk arises from trusting an unpinned, mutable third-party dependency and installing it globally.

Attack Path

  1. An attacker compromises the npm package, its maintainer account, or a future release in its supply chain.
  2. The attacker publishes a release containing malicious package code or lifecycle scripts.
  3. A user follows the Skill and runs npm install -g clawhub without a version constraint.
  4. npm downloads the attacker-controlled latest version.
  5. Malicious lifecycle code executes with the invoking user's permissions, or the globally installed CLI performs malicious actions when subsequently invoked.

Impact Assessment

Exploitation could execute arbitrary code with the permissions of the user running npm. Depending on those permissions and the host configuration, the malicious package could access user-readable files and credentials, alter development tools, intercept future CLI inputs, or modify globally installed ...[truncated 166 chars]

Remediation
View remediation

Remediation Suggestions

  • Pin the CLI to a specifically reviewed version, for example clawhub@1.2.3.
  • Record and verify the expected package publisher, registry, and integrity metadata.
  • Prefer a project-local dependency with a lockfile over a global installation.
  • Disable lifecycle scripts during installation when they are not required, then review any required scripts separately.
  • Document a trusted release-verification process and update the pinned version only after review.
  • Warn users not to run the installation with sudo or unnecessary administrative privileges.

other

Warning
Location
SKILL.md:90
Finding

Guidance for Evading Browser Bot-Detection Controls

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 90–98 and 135–146
Vulnerability Type: Bot-detection evasion guidance
Risk Level: Medium

Vulnerable Code:

markdown
### Pitfall 1: Bot Detection (Vercel Security Checkpoint)
**Symptoms:** "We're verifying your browser" page blocks authentication
**Solution:** 
- Use token authentication (`clawhub login --token --no-browser`)
- For browser auth: Enable Camo Fox + residential proxies in BrowserBase
markdown
## 🦊 Bot Detection & Camo Fox

### When Browser Auth is Required
If you need browser authentication (for token generation):
1. Enable Camo Fox in BrowserBase dashboard
2. Configure residential proxies
3. Use browser with stealth features enabled

### Environment Variables for BrowserBase
```bash
export BROWSERBASE_CAMO_FOX=true
export BROWSERBASE_PROXY_TYPE=residential
text

### Technical Analysis

The Skill explicitly recommends stealth browser features and residential proxies when a Vercel security checkpoint blocks browser authentication. Stealth browser tooling is intended to reduce automation detectability, while residential proxies can disguise the origin and hosting classification of automated traffic.

Combining these controls provides a practical method for making automated browser activity appear more like ordinary residential user traffic. This goes beyond legitimate authentication troubleshooting and may circumvent anti-bot or abuse-prevention controls imposed by the service.

Token-based authentication through the documented CLI command is presented as an alternative and does not require this evasive guidance.

### Attack Path

1. Automated browser authentication is challenged or blocked by the service's security checkpoint.
2. The operator enables Camo Fox or equivalent stealth browser behavior.
3. The operator routes requests through a residential proxy by configuring BrowserBase.
4. Browse
...[truncated 731 chars]
Remediation
View remediation

Remediation Suggestions

  • Remove instructions recommending stealth browser features, Camo Fox, or residential proxies to bypass security checkpoints.
  • Retain only supported token authentication using clawhub login --token TOKEN --no-browser.
  • If browser authentication is blocked, direct users to official ClawHub documentation or support rather than advising evasion.
  • Clearly state that users must comply with ClawHub, BrowserBase, proxy-provider, and authentication-provider policies.
  • If browser automation is officially supported, document only the approved integration and avoid settings designed to conceal automation.
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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

md
[ -f "SKILL.md" ] && echo "✅ SKILL.md exists" || echo "❌ SKILL.md missing"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly advises enabling Camo Fox, residential proxies, and stealth browser features to get around bot-detection barriers during authentication. Even if framed as troubleshooting, this normalizes anti-detection tactics that may violate platform terms, bypass fraud-abuse controls, and expose users to account suspension or compliance issues.

Content

No source excerpt is available for this finding.