ClawHub
Back to skill

Security audit

China Recipe

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese recipe helper with minor documentation inconsistencies, but no evidence of hidden access, persistence, or harmful behavior.

Install this if you want a lightweight Chinese recipe assistant. Treat the English-support and nutrition claims cautiously, and verify dietary, allergy, or health-sensitive cooking advice independently.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: china-recipe
description: 中国菜谱大全。Use when user wants to find Chinese recipes, cooking instructions, ingredient lists, or meal planning. Supports regional cuisines, dietary preferences, and step-by-step cooking guides. 菜谱、烹饪、美食、食谱。
version: 1.0.2
license: MIT-0
metadata: {"openclaw": {"emoji": "🍳", "requires": {"bins": ["python3"], "env": []}}}
---

# China Recipe

中国菜谱大全，支持各大菜系、食材查询、详细做法、营养信息。

## Features

- 🍜 **菜系丰富**: 川菜、粤菜、鲁菜、苏菜、浙菜、闽菜、湘菜、徽菜
- 🥘 *

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The listed trigger conditions include generic phrases such as "做什么菜", "给我一个菜谱", "今天吃什么", and "有什么简单的菜", which are common conversational requests and not narrowly scoped to explicit skill invocation. The file does not provide exclusion conditions or negative examples to clarify when these phrases should not activate the skill.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation explicitly states that the skill does not maintain a recipe database and instead dynamically generates recipes from LLM knowledge. However, the code sample implements a static in-file RECIPES database and a deterministic search function over that data, which directly contradicts the stated working principle.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest description starts in Chinese and presents the skill identity and primary description in a single language, while the policy category requires avoiding forced language or locale without user opt-in. Although later content mentions Chinese and English support, there is no explicit statement that the user can choose their preferred language for interaction.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The documentation says the skill supports both Chinese and English, but the provided data and search logic operate on Chinese recipe names, cuisine labels, and query terms like '简单'. There is no corresponding English recipe corpus, translation layer, or English query handling shown in the code.

Content

No source excerpt is available for this finding.