Back to skill

Security audit

Opc Chain Due Diligence

Security checks across malware telemetry and agentic risk

Overview

This skill performs a disclosed public-data company due-diligence scan, with no evidence of hidden persistence, credential access, destructive actions, or unrelated data collection.

Install only if you are comfortable sending target company names to public third-party services such as Wikidata and USPTO. Do not use confidential acquisition, investment, or investigation targets unless that disclosure risk is acceptable; treat the output as a screening aid, not legal, financial, or investment advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill advertises use of multiple external public APIs and a technical architecture, but it declares no permissions despite requiring network access and likely environment-based configuration. This creates a transparency and governance gap: users and the platform may not realize the skill can transmit queries externally, which can lead to unauthorized data exposure or execution beyond expected trust boundaries.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad, generic business questions that overlap with ordinary user requests such as '帮我查一下' or '帮我看看...综合实力'. This can cause unintended invocation of a networked due-diligence workflow, potentially sending company names or user intent to third-party services when the user did not explicitly request this specific skill.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it uses several third-party public APIs but does not warn users that company identifiers, names, and possibly contextual queries will be transmitted outside the platform. In a due-diligence context, even public-target investigations can be commercially sensitive, so lack of disclosure increases privacy, confidentiality, and compliance risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends the user-supplied company name to third-party services (Wikidata/USPTO) without warning the user that their query will be transmitted externally. In a due-diligence context, company names may be sensitive deal-related targets, so this can leak confidential research intent or non-public business interest to external providers.

External Transmission

Medium
Category
Data Exfiltration
Content
"o": {"per_page": limit, "page": 1}
        }
        try:
            resp = requests.post(USPTO_API_URL, json=query, timeout=30,
                                 headers={"Content-Type": "application/json"})
            if resp.status_code != 200:
                return []
Confidence
97% confidence
Finding
requests.post(USPTO_API_URL, json=

Unpinned Dependencies

Low
Category
Supply Chain
Content
# 运行时依赖通过 coze_workload_identity.requests 提供,无需额外安装
# 以下为开发/测试所需依赖

requests>=2.28.0
Confidence
92% confidence
Finding
requests>=2.28.0

Known Vulnerable Dependency: requests==2.28.0 — 8 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High
Category
Supply Chain
Confidence
95% confidence
Finding
requests==2.28.0

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.