ClawHub
Back to skill

Security audit

patent-project-proposal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PatSnap patent-analysis workflow for generating project proposal reports, with no bundled code or hidden persistence.

Install only if you expect the agent to use PatSnap MCP tools for patent-backed project proposal work. For confidential technical方案 or company strategy, confirm what will be searched before running the workflow, especially when your request merely mentions project initiation without asking for patent analysis.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger examples are broad conversational phrases such as '帮我做立项' and '支撑立项报告', which can overlap with ordinary requests that do not necessarily authorize the full patent-analysis workflow. This can cause the skill to activate unexpectedly and launch extensive MCP-driven data collection and report generation, increasing the chance of unintended external calls and disclosure of user or enterprise context.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description states it triggers when the user clearly mentions project initiation, but it does not define hard boundaries or exclusions for adjacent intents. That ambiguity makes over-triggering more likely, which is risky here because the skill orchestrates many tool calls and may analyze sensitive technical and corporate information once activated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.