Back to skill

Security audit

深度解析Skill技能,输出四部分报告:功能摘要、场景分析、流程图、评分点评,让你一眼看懂优秀技能背后的设计逻辑ub 链接。

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, Markdown-only helper for analyzing user-provided skill packages, with no evidence of hidden execution, persistence, or data theft.

Install only if you want a Chinese-language skill-package reviewer. Provide it only the specific skill archives, links, or paths you want analyzed, since it is designed to read those user-supplied materials.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrases are broad, conversational, and likely to appear in ordinary discussion about skills, which can cause the skill to activate when the user did not intend to invoke it. Unintended invocation is risky here because the skill is designed to fetch, parse, and analyze user-supplied links, files, or local paths, expanding the chance of unauthorized processing or confusing cross-task behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation logic starts the skill on generic phrases without requiring unambiguous context, making accidental execution more likely than a typical command-driven skill. In this skill's context, accidental activation is more dangerous because subsequent steps instruct the agent to accept links, local paths, and uploaded archives, potentially causing unintended access attempts or processing of untrusted content.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
- 根目录下的 `SKILL.md` 或 `skill.yaml`(元数据)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instructions prescribe a Chinese writing style and specific colloquial constraints, effectively forcing one language and tone for outputs. There is no user choice, opt-in, or documented justification for restricting the skill to Chinese responses only.

Content

No source excerpt is available for this finding.