Back to skill

Security audit

迷你厨房烹饪视频

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly coherent WeryAI video-generation helper, but its documented command pattern and endpoint handling create review-worthy risks to the user's shell environment and API key.

Review before installing. Use only official WeryAI endpoints, avoid setting custom WERYAI_BASE_URL or WERYAI_MODELS_BASE_URL unless fully trusted, keep the WeryAI key scoped and rotated, and ensure the runner invokes Node with structured arguments rather than interpolating JSON into a shell command.

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/video_gen.js:20
Finding

API credentials can be redirected to an attacker-controlled endpoint

Content
View full analysis
controller.abort(), 30_000); try { const res = await fetch(fullUrl, { method, headers, body: body != null ? JSON.stringify(body) : undefined, signal: controller.signal, }); ``` ```js async function apiRequest(method, path, body, apiKey) { return httpJson(method, BASE_URL + path, body, apiKey); } async function fetchModelsRegistry(apiKey) { return httpJson('GET', MODELS_BASE_URL + MODELS_API_PATH, null, apiKey); } ``` ### Technical Analysis The script obtains its generation and model-registry origins directly from the `WERYAI_BASE_URL` and `WERYAI_MODELS_BASE_URL` environment variables. It does not verify that the resulting URLs: - Use HTTPS. - Resolve to an approved WeryAI hostname. - Have the expected origin. - Are otherwise trusted to receive the WeryAI credential. The shared `httpJson` function unconditionally places `WERYAI_API_KEY` in the `Authorization` header for requests to either configured origin. Consequently, an actor capable of influencing the process environment can redirect authenticated requests to an arbitrary HTTP or HTTPS server. Sending the API key to the official WeryAI API is necessary for the declared video-generation functionality. Allowing the credential to be sent to unrestricte ...[truncated 1911 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:62
Finding

User-derived JSON may enable shell command injection through the documented invocation pattern

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill is presented as a narrowly scoped 'mini-kitchen video' generator, but the underlying behavior appears more general-purpose, including broader video generation flows, multi-image support, model enumeration, and task-status querying. That mismatch is dangerous because users and reviewers may approve the skill based on a much narrower trust assumption than what the implementation can actually do, enabling capability creep and covert misuse of external APIs.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
**依赖**:本目录 `scripts/video_gen.js` + 运行环境需设置 `WERYAI_API_KEY` + Node.js 18+。不依赖其他 Cursor 技能。

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a Node script, requires an API key in the environment, and makes network-backed video generation requests, yet it declares no explicit tool scope or permissions boundary. This creates an avoidable least-privilege gap: an agent or platform may grant broader execution or network access than users expect, reducing transparency and increasing the blast radius if the script is modified or misused.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's user-facing instructions and invocation flow are entirely written in Chinese, including required confirmation phrases such as replying with "确认" or "循环". This creates an implicit language constraint without documenting user choice or opt-in, which matches the locale/language policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-level CLI description, commands context, examples, and environment-variable documentation are written in Chinese only. This imposes a specific language on users without offering a language choice or documenting a justified locale restriction, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.