Back to skill

Security audit

WorksHub

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real WorksHub bridge, but it can spend or change marketplace/account state and handle API credentials without enough guardrails or disclosure.

Review this skill before installing. Only use it with a tightly scoped WorksHub API key, do not set WORKSHUB_API_URL to an untrusted endpoint, avoid running financial or state-changing tools unless the user has explicitly approved the exact action, and treat command output as potentially sensitive after login or API-key creation.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
bridge.js:9
Finding

API Credential Disclosure Through an Unrestricted Configurable Endpoint

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
bridge.js:213
Finding

Newly Created API Credentials May Be Exposed Through Standard Output

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
bridge.js:120
Finding

Unencoded Path Parameters Can Alter Authenticated API Routes

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (11)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · .clawhubignore.txt (reported line 4)May include surrounding context.

text
node_modules/
*.log
.DS_Store
.env

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill supports payment-relevant and potentially irreversible actions such as creating bounties, accepting applications, canceling tasks, and obtaining payment QR codes, yet it does not prominently warn that these operations may trigger financial commitments or irreversible workflow changes. In an agentic setting, insufficient disclosure raises the risk of accidental spending, unintended commitments, or unauthorized marketplace actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill supports payment-relevant and potentially irreversible actions such as creating bounties, accepting applications, canceling tasks, and obtaining payment QR codes, yet it does not prominently warn that these operations may trigger financial commitments or irreversible workflow changes. In an agentic setting, insufficient disclosure raises the risk of accidental spending, unintended commitments, or unauthorized marketplace actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language usage instructions and descriptions are presented only in Chinese, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly documented as region-specific and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The code exposes a DELETE operation to cancel a bounty, which is a potentially irreversible action. While the tool description names the action, there is no confirmation prompt, explicit warning comment/docstring near execution, or other user-facing disclosure before the request is sent.

Content

No source excerpt is available for this finding.

Lp4

Low
Category
MCP Least Privilege
Confidence
65% confidence
Finding

Declared permissions with no matching code capability may indicate removed functionality or pre-staging for future abuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The script reads WORKSHUB_API_KEY from the environment and uses it for authenticated requests, but there is no user-facing disclosure that the tool consumes credential material from environment variables. For code files, sensitive environment-variable access should have some visible explanation via comments, logging, prompt, or accompanying markdown warning.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The inline comment says 'create_api_key 使用 Bearer Token', but there is no create_api_key tool in TOOL_MAP and no mapped tool sets useBearer. As written, this documented authentication path is dead code, so the comments describe behavior the skill does not actually expose.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The dependency uses a caret range (^1.7.7), which allows newer minor and patch releases to be installed without explicit review. This weakens build reproducibility and can silently introduce vulnerable or malicious upstream changes, especially for a network-capable skill that relies on HTTP requests.

Content

Scanner excerpt · package.json (reported line 6)May include surrounding context.

json
"version": "1.0.3",
  "type": "module",
  "dependencies": {
    "axios": "^1.7.7"
  }
}

Unverifiable Dependency: axios has 16 known advisory(ies) (CVE-2026-44494 (axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `co); CVE-2026-44495 (axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollut); CVE-2025-62718 (Axios has a NO_PROXY Hostname Normalization Bypass that Leads to SSRF) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
86% confidence
Finding

The manifest references axios without exact pinning, while the package has multiple known advisories across versions. Because the allowed range can resolve to different releases and the exact installed version is not verifiable from this file alone, the skill may consume an affected axios version, which is more concerning here because the skill has outbound network access to workshub.ai and axios is central to request handling.

Content

No source excerpt is available for this finding.