ClawHub
Back to skill

Security audit

tag-patent-search-results-ip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent patent-tagging workflow with disclosed file outputs, human review boundaries, and no evidence of hidden execution or data exfiltration.

Before installing, make sure the patent candidate files and any MCP connector use are authorized for your project, especially if the dataset contains confidential or licensed patent work. The skill is designed to keep full-pool tagging as a human-controlled handoff and should not be used to auto-fill human review fields.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 353)May include surrounding context.

md
Record taxonomy/schema version, required/optional columns, allowed values, multi-label
delimiter, row count, identifier checksum, file checksum, generation date, privacy
boundary, and return instructions in `tech_breakdown.json.meta` and the handoff summary.

## Step 9 — Validate Stage 3 outputs

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explicitly labels an 'English marketplace' and separately notes a 'Chinese source page' only in a parent localization index, but it does not state that users may choose their preferred language or locale. This can be read as a language/locale constraint in the skill documentation without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction says every node must have a human-readable English display name, which imposes a specific language requirement in natural-language guidance. The file does not offer user opt-in for language selection or explain why English is required for a region-specific or compliance reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.