Back to skill

Security audit

Data Analysis Report

Security checks for vulnerabilities and agentic risk

Overview

This is a local data-analysis/reporting skill with no hidden network, credential, persistence, or destructive behavior found.

Reasonable to install if you want local data-report generation. Use a virtual environment, consider pinning or reviewing dependencies, and only point it at datasets you intend to analyze. Expect Chinese-language reports unless you customize the skill or ask the agent to translate output.

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:24
Finding

Unpinned Third-Party Dependencies

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 24-29
Vulnerability Type: Unpinned third-party dependencies
Risk Level: Medium

Complete Snippet:

bash
Installation requirements (automatically handled):
pip install pandas matplotlib seaborn plotly jupyter openpyxl

Technical Analysis

The documented installation command retrieves several packages and their transitive dependencies without exact version constraints, cryptographic hashes, a reviewed lock file, or an explicitly trusted package index. Consequently, installation results can change over time and may include releases that were not reviewed as part of this Skill.

This creates a supply-chain exposure: if a named package, one of its transitive dependencies, or the package repository is compromised, malicious code could run during package installation or when the installed package is imported. The audit did not find evidence that any currently named package is malicious; the vulnerability is the unsafe dependency-resolution practice itself.

Attack Path

  1. An attacker compromises a referenced package or one of its transitive dependencies and publishes a malicious release to the package source used by pip.
  2. A user or automation follows the installation command from SKILL.md.
  3. Because no versions or hashes are pinned, pip may resolve and install the attacker-controlled release.
  4. Malicious package code executes during installation or when the processor imports the affected package.
  5. The payload runs with the privileges and environmental access of the user executing the installation or Skill.

Impact Assessment

Successful exploitation could provide arbitrary code execution under the installing user's account. The resulting scope may include access to files, environment variables, datasets, and network resources available to that account. It does not inherently grant elevated system privileges; broader access woul ...[truncated 104 chars]

Remediation
View remediation

Remediation Suggestions

  1. Move dependencies into a reviewed lock or requirements file with exact versions.

  2. Record cryptographic hashes and enforce them during installation:

    bash
    python -m pip install --require-hashes -r requirements.txt
    
  3. Pin all transitive dependencies, not only direct dependencies.

  4. Configure an approved package index and prevent unintended fallback to untrusted indexes.

  5. Regularly scan locked dependencies for known vulnerabilities and update them through a controlled review process.

  6. Install dependencies in an isolated virtual environment using a non-privileged account.

  7. Replace the claim that installation is “automatically handled” with precise, reproducible setup instructions.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill states '中文优化:对中文数据自动适配,输出中文报告', which effectively sets Chinese output as the default behavior without presenting a user choice. While not a classic security flaw, forced language behavior can reduce user comprehension of results, warnings, or privacy-relevant prompts, especially in multilingual environments, and may contribute to unsafe approval of actions the user does not fully understand.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are generic natural-language requests such as '分析这个数据' and 'generate data insights report', which are likely to overlap with ordinary user prompts. This can cause unintended invocation of the skill on unrelated conversations or sensitive local files, increasing the chance of unexpected data processing and report generation without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module docstring and embedded report/template text are entirely in Chinese, indicating the skill is designed to operate in a fixed language/locale. The file does not provide any user opt-in, configuration, or documented justification for restricting outputs to Chinese, which is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.