ClawHub
Back to skill

Security audit

企业-产学研合作与研发评估

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only research skill for public company-academia collaboration analysis, with no hidden execution, persistence, or credential handling found.

Install this if you want Chinese-language public-source analysis of a company’s university and research-institute collaborations. Treat forward-looking moat and investment-style judgments as analytical estimates, and verify important business decisions against primary sources.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written to operate exclusively in Chinese and prescribes Chinese-language outputs without giving the user a language choice or documenting a necessary locale restriction. In multi-language environments, this can degrade transparency and correctness by surprising users, hindering review, and increasing the chance that important caveats or sourcing nuances are missed.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill’s activation criteria are broad enough to trigger on generic company-analysis requests such as assessing R&D strength, technology sources, or external research relationships. This can cause unintended invocation, leading the agent to perform networked collection and produce speculative strategic assessments outside the user’s precise intent, increasing the risk of over-collection and misleading outputs.

Content

No source excerpt is available for this finding.