T03 · Remote Payload Retrieval and Execution
- Location
SKILL.md:75- Finding
Unpinned Remote Installer Scripts Are Downloaded and Immediately Executed
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:75Unpinned Remote Installer Scripts Are Downloaded and Immediately Executed
SKILL.md:70Globally Installed npm Dependency Is Mutable and Version-Unpinned
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.
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
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.
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
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.
# 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
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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
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.
# 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
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.
## 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.
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.
## 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.
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.
## 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.
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.
## 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
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.
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.