Security audit

YiHui GIT MONITOR

Security checks for vulnerabilities and agentic risk

Overview

This Git monitoring skill has a coherent purpose, but it asks for automatic repository syncing, scheduled checks, external notifications, and raw Feishu credential access without enough scoping or inspectable implementation.

Review this before installing if you use private repositories or Feishu. Only enable scheduled checks and Feishu notifications for repositories and chats you explicitly approve, and use narrowly scoped Feishu credentials that can be rotated. Because the referenced helper.js is not present in the reviewed artifact, do not assume secret handling, logging, network destinations, or local repository changes are safely constrained.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:89
Finding: Automatic Access to Raw Feishu Credentials
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The top-level description says the skill can monitor repositories and auto-pull code, but it does not clearly warn that using the skill may modify local workspace state and send repository activity notifications externally. That omission can mislead users into invoking the skill without understanding its side effects, which is particularly sensitive for private/internal repositories or environments where automatic code sync is risky.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes broad, generic phrases such as “GitHub”, “GitLab”, “Gitee”, “代码变化”, and “拉取代码”, which can plausibly appear in ordinary conversation and cause unintended skill activation. In this skill’s context, accidental invocation is more dangerous because the documented behavior includes automatically pulling repositories and sending notifications, which can change local state and disclose repository activity without a clearly scoped user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description, triggers, and usage examples are entirely in Chinese, and the trigger phrases are Chinese-only. The file does not indicate that the skill is region-specific or offer an opt-in or alternative language, which can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.