Back to skill

Security audit

Excel Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Excel file builder, with minor caution needed around broad triggers and unpinned package installation instructions.

Before installing, confirm you want the agent to create or modify Excel files. If dependencies are missing, prefer installing pinned versions in a dedicated virtual environment rather than letting an agent run unpinned pip installs in a shared environment.

Vulnerability Patterns
  • 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
  • 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 (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:69
Finding
Unpinned Third-Party Dependency Installation## Vulnerability Details **File Location**: `SKILL.md`, lines 69–70 **Vulnerability Type**: `T08: Insecure Dependencies` **Risk Level**: Medium **Vulnerable Code**: ```text - If `openpyxl` not installed: `pip install openpyxl` - If `xlsxwriter` not installed: `pip install xlsxwriter` ``` ### Technical Analysis The Skill instructs the agent to install third-party Python packages without exact version constraints, integrity hashes, an explicitly approved package index, or user confirmation. Consequently, package contents and transitive dependencies can vary between executions. Python package installation can execute package build and installation logic. If a package source, release, dependency, or configured package index is compromised or substituted, attacker-controlled code could execute during installation. The absence of a lock file and hash verification prevents the installer from confirming that the resolved artifacts are the versions reviewed and approved by the project. ### Attack Path 1. A user invokes the Excel Builder Skill in an environment where `openpyxl` or `xlsxwriter` is unavailable. 2. The agent follows the documented error-handling instruction and executes the corresponding unpinned `pip install` command. 3. `pip` resolves the current package release and its transitive dependencies through the environment's configured package index. 4. A compromised index, package release, or transitive dependency supplies malicious installation or runtime code. 5. The malicious code executes with the privileges of the account running `pip` and may subsequently run again when the installed library is imported. ### Impact Assessment Successful exploitation could provide arbitrary code execution under the privileges of the agent or user performing the installation. The affected scope may include files, environment variables, credentials, network resources, and services accessible to that account. If installation is perfo ...[truncated 184 chars]
Remediation
## Remediation Suggestions - Remove automatic or implicit dependency installation instructions from the Skill workflow. - Require explicit user approval before installing any package. - Define reviewed dependencies in a lock file or requirements file using exact versions. - Record and enforce cryptographic hashes for all direct and transitive dependency artifacts. - Install with a command such as `python -m pip install --require-hashes -r requirements.txt`. - Configure an approved package index and disable unintended fallback indexes. - Perform installation inside a dedicated, least-privileged virtual environment or isolated container. - Periodically scan and update locked dependencies through a controlled review process.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list is very broad and includes generic terms such as "Excel", "spreadsheet", "formula", and library names like "openpyxl" and "xlsxwriter", which can cause the skill to activate for many loosely related requests. Over-broad invocation increases the chance of unintended tool use, incorrect routing, or an attacker steering execution toward file-generation behavior when the user did not explicitly request it.

Static analysis

No suspicious patterns detected.