Back to skill

Security audit

vaDeepresearch

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed deep-research/report-writing skill that uses available research tools and produces Markdown reports, with no evidence of hidden execution, persistence, credential access, or exfiltration.

Before installing, expect this skill to perform external research and create Markdown report files for analysis-style requests. Use explicit wording if you only want a short answer or no web research.

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
  • 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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s trigger scope is broad enough to activate on many ordinary requests for 'analysis' or 'research,' which can cause unintended routing into a heavyweight workflow with mandatory file generation and web/tool usage. In an agent setting, this increases the chance of over-collection, unnecessary external access, and confusing behavior when the user did not ask for deep research.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The English trigger phrases include generic formulations like 'quick analysis of' and 'comprehensive analysis of,' which are common in normal assistant interactions and may spuriously invoke this skill. Because the skill then directs the agent toward multi-source retrieval and mandatory Markdown artifact delivery, accidental activation can expand data exposure and tool usage beyond user expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains user-facing natural-language content exclusively in Chinese, including the title, headings, body text, and closing prompt. Under the policy rule for language/locale constraints, forcing a specific language without opt-in or justification can violate organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing natural language entirely in Chinese, including the title, headings, and all instructions, but it does not indicate that Chinese is optional or that the skill is intended only for a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing natural language entirely in Chinese, including the title, headings, recommendations, and follow-up options. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation unless the restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

技能清单描述明确强调“必须输出 Markdown(.md)文件,并提供下载地址或可直接打开的文件入口”,而该参考文件在后续处理部分主动扩展到 Word、PDF、PPT、HTML、Excel 等格式。对于一个以深度研究和 Markdown 交付为核心的技能,这体现出交付行为与描述存在轻微偏移。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file is natural-language content, so language-policy checks apply. The title, headings, body text, and closing note consistently require Chinese reading ability, and there is no indication that users can request another language or that the report is intended only for a China-specific audience as a documented constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.