Back to skill

Security audit

build-patent-asset-dashboard-ip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PatSnap patent-data workflow with expected API use, though users should handle the PatSnap API key carefully.

Install only if you intend to use PatSnap services for patent dashboard data. Use a narrowly scoped PatSnap API key, prefer PATSNAP_API_KEY or a secret manager instead of --api-key, avoid untrusted applicant-name input unless it is validated or escaped, and verify PatSnap endpoint availability before relying on generated counts.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/p002_applicant_search.py:59
Finding

Bearer Token Exposure Through Command-Line Argument

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/p002_applicant_search.py:20
Finding

PatSnap Query Injection Through Unescaped Applicant Name

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description promises substantial patent-data retrieval and analytics functionality tied to PatSnap APIs. The actual code chunk contains only a minimal script entry point that prints a static message when run. There is no evidence of API calls, data-layer construction, analytics computation, or dashboard-oriented processing. This is a material description-to-behavior mismatch because the implemented behavior does not meaningfully realize the declared purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 358)May include surrounding context.

md
## MCP and API configuration

This source package is primarily a PatSnap REST API workflow. It does not contain a README and no new setup file may be added without approval.

- Authenticate REST calls with a PatSnap Open Platform API key.
- Verify each endpoint in the current [PatSnap Developer Center](https://open.patsnap.com/devportal) before execution.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/p002_applicant_search.py (reported line 30)May include surrounding context.

python
"page": page,
        "page_size": page_size
    }
    resp = requests.post(API_URL, headers=headers, json=payload, timeout=30)
    resp.raise_for_status()
    data = resp.json()
    if not data.get("status"):

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The instruction says to default to lang: en for the global dashboard and use other languages only in limited cases. This imposes a language preference in natural-language guidance rather than offering a neutral user choice, which can conflict with language/locale policy expectations unless the user has opted in.

Content

No source excerpt is available for this finding.