Back to skill

Security audit

create-patent-landscape-overview-ip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed patent-landscape workflow that uses patent-data connectors and human checkpoints without hidden execution, persistence, or destructive behavior.

Install only if you intend to use PatSnap patent-data connectors and are comfortable with English workflow outputs. Review generated project files for confidentiality, and keep the built-in human approval and legal-boundary checkpoints in place for tagging, asset signals, and counsel follow-up.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hard-codes use of an English interface and English output without tying that requirement to a technical constraint, compliance need, or explicit user preference. In a workflow that handles nuanced patent-search scope, legal-signal caveats, and human handoff, forcing English can degrade user comprehension, increase mis-scoping risk, and undermine informed review for non-English users.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 566)May include surrounding context.

md
- taxonomy and schema versions.

The user or authorized reviewer must approve the taxonomy before Stage 3.5.
Do not auto-approve this checkpoint.

## Stage 3.5 — Genuine human tagging handoff

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L087 specifies display_name as a "Clear international English term," which imposes a language requirement in the skill's instructions. The file does not offer a user language choice or explain a justified locale constraint, so this is a natural-language policy issue under the language/locale rule.

Content

No source excerpt is available for this finding.