Security audit

Implicit Contract Defense

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Rust/SeaORM contract-checking workflow with local scripts and no evidence of hidden network access, persistence, credential access, or destructive behavior.

Install only if you are comfortable with Chinese-language guidance or can translate it. Run gen_types.sh intentionally because it executes cargo test in your project and overwrites the TypeScript file path you provide.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The declared description presents a high-level defensive development规范/architecture pattern for Rust + SeaORM + frontend + database projects. The supplied code does not implement repository isolation, SeaORM-related constraints, or boundary-defense logic. Instead, it is a utility script for generating and merging TypeScript type definitions from Rust via ts-rs. This is a materially different primary purpose and involves concrete filesystem and build-step behavior not reflected in the description.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This markdown file contains the skill’s operational description entirely in Chinese, including activation criteria and agent guidance. Under the stated policy, forcing a specific language without giving the user a language or locale choice is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This shell script embeds its title, usage notes, and agent instructions entirely in Chinese, which imposes a specific language on users and maintainers. Under the policy, locale or language constraints should either provide user choice or be clearly justified as region-specific; neither is present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The script's runtime output, warnings, and summary messages are all hard-coded in Chinese, so anyone invoking the skill receives a forced locale experience. This is a natural-language policy issue because the file does not offer an alternative language or explain a justified regional restriction.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.