Security audit

Code Review

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only code review skill whose code-reading behavior matches its stated purpose and does not show hidden execution, exfiltration, or persistence.

Reasonable to install for code review. Use it when you intend the agent to inspect code or diffs, and request English output explicitly if Chinese is not desired.

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 (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The README states '中文优先' for review reports and explanations without offering user choice or an opt-in mechanism. In multi-user or multilingual environments, forced language output can cause misunderstanding of security findings, incorrect remediation, or accidental disclosure through translation workarounds, though the direct security impact is limited. The code-review context slightly increases risk because accurate comprehension of security advice is important, but this is primarily a usability and safety-control issue rather than a severe exploit path.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill advertises very broad natural-language trigger phrases such as general requests to review code or check whether code has problems. In an agent environment, overly broad triggers can cause unintended invocation on ordinary conversation or unrelated content, creating prompt-routing confusion and increasing the chance that sensitive code, diffs, or context are sent to this skill without clear user intent. The context makes this more dangerous because the skill is positioned as a general code-review tool and includes multiple generic activation examples, which raises the likelihood of accidental activation during normal developer chats.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match common requests like '帮我看看代码' or general mentions of code quality, which can cause the skill to activate when the user did not explicitly ask for this specialized review workflow. Unintended invocation increases the chance of unnecessary file access or git-diff-based review behavior, especially because the skill later instructs the agent to proactively inspect local changes.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file presents the review rules primarily in Chinese, beginning with a Chinese title and bilingual subtitle, but it does not state that the language is optional or limited to a region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Line L208 explicitly requires that the review output be in Chinese. This is a natural-language locale constraint with no opt-in or alternative language option, which violates the policy against forcing a specific language without user choice.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The condition '需要检查代码安全性、性能、可维护性' is ambiguous because it describes a broad class of developer assistance rather than a clearly bounded invocation trigger. In practice, this can over-select the skill for routine conversations about code quality, leading to unnecessary or unexpected review actions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.