Back to skill

Security audit

Laiye ADP Global Document Intelligent Extraction · Fast

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent invoice-extraction purpose, but its setup instructions include unsafe unpinned remote code execution and global package installation for a cloud service that handles sensitive financial documents.

Review this skill before installing. Prefer a pinned, verified release or reviewed binary over the curl|bash or irm|iex commands, avoid running npm or installers with administrator/root privileges, and confirm your organization permits sending invoice, receipt, and billing documents to the ADP cloud service. Treat the ADP API key as a secret and avoid using the skill on regulated or confidential documents without approval.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:75
Finding

Unpinned Remote Installer Scripts Are Downloaded and Immediately Executed

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
SKILL.md:70
Finding

Globally Installed npm Dependency Is Mutable and Version-Unpinned

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (19)

Chaining Abuse

High
Category
Tool Misuse
Confidence
98% confidence
Finding

Piping network-fetched content directly into bash removes any meaningful opportunity for inspection and turns a documentation example into an immediate arbitrary-code-execution primitive. In a skill meant for installation by agents or operators, this is especially dangerous because it normalizes unsafe command chaining during setup.

Content

Scanner excerpt · README-CN.md (reported line 30)May include surrounding context.

md
npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli

# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash

# Windows(PowerShell)
irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex

Chaining Abuse

High
Category
Tool Misuse
Confidence
99% confidence
Finding

The | bash pattern is a classic chaining-abuse primitive because it eliminates any review boundary between untrusted network content and local execution. In this skill's context, users are explicitly told to run it for setup, so exploitation would likely yield immediate code execution with the user's privileges and potentially access to local documents and stored API credentials.

Content

Scanner excerpt · README.md (reported line 32)May include surrounding context.

md
npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli

# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash

# Windows (PowerShell)
irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex

Chaining Abuse

High
Category
Tool Misuse
Confidence
99% confidence
Finding

The | bash chaining pattern is especially dangerous because it converts network-delivered content directly into shell execution with no validation or inspection step. In an agent skill context, this can normalize unsafe command execution and increase the chance that users or downstream automation run untrusted code verbatim.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

bash
# Method 2: Shell script (Linux / macOS, when npm is unavailable)
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
bash

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README instructs users to fetch and immediately execute remote shell and PowerShell scripts using a pipe to bash/iex, without any integrity verification, pinning, or review step. If the hosted script, distribution channel, or upstream account is compromised, users may execute arbitrary code on their machines during installation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill encourages parsing local files, directories, and remote URLs through a cloud API but does not clearly disclose that document contents may be transmitted to a third-party remote service. In the context of invoices, receipts, and financial records, this can expose sensitive personal, financial, and business data and create compliance or confidentiality risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README instructs users to install by piping remote scripts directly into a shell (bash/iex) without any integrity verification, pinning, or warning about system changes. If the upstream script, hosting account, or network path is compromised, users could execute arbitrary code on their machines during installation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The examples encourage parsing local documents and remote URLs through a cloud API but do not warn that invoice files may contain highly sensitive financial, personal, or contractual data that will be transmitted to a third-party service. In a finance-oriented skill, this omission increases the risk of accidental data exposure, compliance violations, and inappropriate handling of confidential documents.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to submit invoice files and receive structured extraction results from a remote ADP service, but it does not clearly warn that potentially sensitive financial documents and extracted business data will leave the local environment. Invoices commonly contain PII, banking, tax, supplier, and customer data, so lack of an explicit disclosure/consent notice can lead to unintended data exposure and policy violations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The installation section includes remote bootstrap commands that download and immediately execute code from the network, but it does not warn users that these commands will run fetched scripts on the local machine. This creates a supply-chain and arbitrary code execution risk if the source is compromised, the URL changes, or the content is intercepted in a trusted environment.

Content

No source excerpt is available for this finding.

External Script Fetching

Low
Category
Supply Chain
Confidence
95% confidence
Finding

This line explicitly downloads a script from GitHub and executes it, creating a classic supply-chain and remote-code-execution risk. Even if the vendor is legitimate, users are asked to trust the network path and current repository state at execution time.

Content

Scanner excerpt · README-CN.md (reported line 30)May include surrounding context.

md
npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli

# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash

# Windows(PowerShell)
irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The documentation tells users to configure an API key but does not warn that the credential grants access to a paid cloud service and may expose document-processing capability if leaked. Users may paste keys into shells, logs, screenshots, shared configs, or automation environments without understanding the sensitivity.

Content

No source excerpt is available for this finding.

External Script Fetching

Low
Category
Supply Chain
Confidence
98% confidence
Finding

The command fetches a script from GitHub and immediately executes it, creating a direct remote-code-execution path during installation. Any compromise of the repository, maintainer account, DNS/TLS trust chain, or referenced script content could result in arbitrary commands running on the user's system.

Content

Scanner excerpt · README.md (reported line 32)May include surrounding context.

md
npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli

# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash

# Windows (PowerShell)
irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex

External Script Fetching

Low
Category
Supply Chain
Confidence
98% confidence
Finding

curl -fsSL ... | bash fetches a script from GitHub and pipes it directly into a shell, giving remote content immediate execution privileges on the host. If the repository, dependency chain, or transport trust is compromised, the command can execute arbitrary code without review.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

bash
# Method 2: Shell script (Linux / macOS, when npm is unavailable)
curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
bash

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · license.md (reported line 10)May include surrounding context.

md
## 1. Licensing

1.1 Free Use and Distribution: The Licensor grants the Licensee a non-transferable, non-exclusive right to freely use, copy, publish, and distribute copies of the Product for non-commercial purposes. The aforementioned "non-commercial purposes" include, but are not limited to:

•   Personal learning, research, teaching, and evaluation.  
•   Technical exchanges within academic institutions or open-source communities, non-profit projects.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · license.md (reported line 16)May include surrounding context.

md
## 1. Licensing

1.1 Free Use and Distribution: The Licensor grants the Licensee a non-transferable, non-exclusive right to freely use, copy, publish, and distribute copies of the Product for non-commercial purposes. The aforementioned "non-commercial purposes" include, but are not limited to:

•   Personal learning, research, teaching, and evaluation.  
•   Technical exchanges within academic institutions or open-source communities, non-profit projects.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · license.md (reported line 25)May include surrounding context.

md
## 1. Licensing

1.1 Free Use and Distribution: The Licensor grants the Licensee a non-transferable, non-exclusive right to freely use, copy, publish, and distribute copies of the Product for non-commercial purposes. The aforementioned "non-commercial purposes" include, but are not limited to:

•   Personal learning, research, teaching, and evaluation.  
•   Technical exchanges within academic institutions or open-source communities, non-profit projects.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · license.md (reported line 38)May include surrounding context.

md
## 4. Disclaimer of Warranties

THE PRODUCT IS PROVIDED "AS IS", WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO: THE LICENSOR DOES NOT WARRANT THAT THE PRODUCT IS FREE FROM ERRORS, BUGS, WILL OPERATE PROPERLY, OR IS SUITABLE FOR A PARTICULAR PURPOSE; THE LICENSOR DOES NOT WARRANT THAT USE OF THE PRODUCT WILL NOT INFRINGE UPON THIRD-PARTY RIGHTS; THE LICENSOR SHALL NOT BE LIABLE TO THE LICENSEE OR ANY THIRD PARTY FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, OR PUNITIVE DAMAGES ARISING FROM THE USE OF THE PRODUCT.

## 5. Termination

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language terms require disputes to be governed by the laws of the People's Republic of China and litigated in the Licensor's local court. Under the policy rule for language/locale-style constraints, this is a fixed locale/jurisdiction requirement presented without user choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The Chinese version likewise fixes PRC law and the Licensor's local court as mandatory dispute-resolution terms. This is a natural-language locale/jurisdiction constraint that is not framed as optional or user-selected.

Content

No source excerpt is available for this finding.