Security audit

jp-patent-claims-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent patent-claims review workflow that uses disclosed patent-search integrations and writes a local HTML report.

Before installing, confirm you are comfortable providing patent application content to the configured Zhihuiya MCP search service and with the skill creating or replacing @skill_workspace/report.html as its output report.

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
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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The skill mandates saving the full review result to @skill_workspace/report.html, which is a file write operation. Although the behavior is documented elsewhere in the file, this section does not include a clear user warning about local file creation or overwriting implications.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.