T09 · Insecure Skill Coding Practices
- Location
bridge.js:9- Finding
API Credential Disclosure Through an Unrestricted Configurable Endpoint
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
bridge.js:9API Credential Disclosure Through an Unrestricted Configurable Endpoint
bridge.js:213Newly Created API Credentials May Be Exposed Through Standard Output
bridge.js:120Unencoded Path Parameters Can Alter Authenticated API Routes
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
node_modules/
*.log
.DS_Store
.env
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
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.
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.
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.
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.
Declared permissions with no matching code capability may indicate removed functionality or pre-staging for future abuse.
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.
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.
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.
"version": "1.0.3",
"type": "module",
"dependencies": {
"axios": "^1.7.7"
}
}
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.