Security audit

debug-pro

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only debugging-method skill with read-oriented tool access and no evidence of hidden code, persistence, exfiltration, or destructive behavior.

Installers should treat this as a Chinese-first debugging workflow aid. Review the broad trigger words and licensing ambiguity if those matter in your environment, but there is no artifact evidence of hidden execution, persistence, credential use, network retrieval, or destructive actions.

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 (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.
md
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**：保留所有权利（All rights reserved） |

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest lists trigger keywords as just "debug" and "pro", which are not specific enough to this skill's intended use. "debug" is a common development term and "pro" is especially broad, creating a risk of unintended invocation without any limiting context or negative examples.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The documentation first states "本包无独立代码文件（纯文档/理论件）" and that code in the package would be MIT-licensed, but later says the package is entirely documentation/theory and therefore "不适用任何代码许可（含 MIT / Apache-2.0）". These statements actively conflict about the package contents and applicable license scope, creating an intent/documentation divergence within the skill file itself.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description embeds a long trigger list containing broad phrases such as “debug”, “bug”, “报错”, and “定位问题”, which are common in ordinary developer conversations. Overly broad activation phrases can cause unintended invocation of the skill, leading to prompt-routing mistakes, user confusion, and possible exposure of the skill’s debugging guidance in contexts where it was not requested.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description is entirely in Chinese and presents the skill behavior and trigger phrases in that language, with no indication that users may choose another language or locale. Under the policy, language-specific behavior should be opt-in or clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.