Back to skill

Security audit

opd-data

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent OPD financial-data client, but it needs review because its API-key handling is weaker than its stated safety boundary.

Install only if you trust OPD and are comfortable storing an OPD API key locally. Prefer a restricted account/key, check permissions on ~/.opd/api_key, avoid sharing keys in chat or logs, and treat results containing contact, shareholder, salary, birth-date, or resume fields as sensitive.

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

Error
Location
scripts/opd_query.py:146
Finding

API Key Exposure Through Unvalidated Cross-Origin Redirects

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/opd_query.py:109
Finding

Plaintext API Key File Created Without Explicit Restrictive Permissions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (14)

Tainted flow: 'req' from os.environ.get (line 162, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/opd_query.py (reported line 167)May include surrounding context.

python
"Accept": "application/json",
    })
    try:
        with urllib.request.urlopen(req, timeout=60) as resp:
            body = resp.read().decode("utf-8")
    except urllib.error.HTTPError as e:
        body = e.read().decode("utf-8", "replace")

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
### 财务信息(references/catalog_finance.md,16 个接口)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill performs privileged actions—reading environment variables, writing a local API key file, and making outbound network requests—but does not declare an explicit tool scope such as permissions or allowed-tools. That creates a governance gap: the runtime and reviewers cannot enforce least privilege from the manifest alone, increasing the chance of unintended capability exposure or future drift beyond the documented behavior.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 25)May include surrounding context.

环境准备(首次使用,一次性)

  1. 获取 API Key:由 OPD 平台分配,形如 opd_xxx。注册/订阅等管理操作在 https://data.originp.com/ 完成(该站提供页面服务);https://api.originp.com 为接口调用地址,专供程序调用、不含页面。注意:除 Key 外还需订阅所需接口(试用或购买套餐),未订阅的接口调用会返回 BIZ_INTERFACE_FORBIDDEN。
  2. 配置 API Key(推荐:终端交互输入):指引用户在本地终端运行:
    bash
    python scripts/opd_query.py --set-key
    

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file documents authenticated access via X-API-Key and multiple endpoints that return named shareholders, management personnel, resumes, birth dates, salaries, and related governance data. Under the markdown-file criteria, the description should warn users about privacy, credential handling, or data-sensitivity impacts, but no such warning appears near the authentication or dataset descriptions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all operational instructions, parameter descriptions, and usage details exclusively in Chinese. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file includes authentication instructions using the X-API-Key header, which is a credential-bearing operation. The document explains how to supply the key but does not include any user warning about keeping the key secret, avoiding client-side exposure, or handling it securely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The file again instructs users to send X-API-Key: opd_xxx for authentication but provides no warning about credential sensitivity. Because this is user-facing markdown documenting credential use, a short disclosure about safe handling is warranted.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This section tells users to authenticate with an API key header but does not mention any privacy or security implications of using a secret credential. In markdown documentation, omission of such a warning can lead to unsafe handling or accidental disclosure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The markdown specifies an X-API-Key value for authenticated access but provides no warning about safeguarding that key. Since the skill description covers behavior affecting credential handling, it should disclose the sensitivity of the secret.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This section documents passing an API key in the request header but contains no warning about secure storage or accidental leakage. For markdown files, omission of warnings around credential use is a relevant quality and safety issue.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The file repeatedly instructs use of X-API-Key: opd_xxx yet never warns users about credential confidentiality. That omission reduces safety for a skill description involving authenticated access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file documents requests requiring an X-API-Key header, which affects user privacy and system integrity because it involves credential use. The page provides authentication details but no caution about protecting the key, avoiding exposure in logs/shared examples, or using secure storage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

该 markdown 文档从标题到全部接口说明均仅以中文呈现,没有说明可切换语言、可提供英文版本,或该语言限制仅适用于特定地区/用户群。根据规则,强制单一语言而无用户选择可能构成语言/locale 政策问题。

Content

No source excerpt is available for this finding.