Back to skill

Security audit

Data Analysis Plus

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward data-analysis template skill with explicit local examples and no hidden execution, persistence, credential access, or network behavior.

Reasonable to install for data-analysis assistance. Before running copied snippets, review file paths and output filenames, especially the PNG save examples, because they may overwrite files with the same names in the working directory.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The function name 'sample_size计算器' mixes English with Chinese, introducing a language-specific element in the skill content. The file does not state that the skill is intended for a Chinese-speaking context or provide a user language choice, which may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file describes 'Automated Reports' and later includes examples that save outputs to disk, such as generated images. The skill description does not warn users that using these templates will create or overwrite local files, which is a user-impacting behavior covered by the missing-warning rule for markdown files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The Python visualization template uses multiple plt.savefig() calls to write trend.png, scatter.png, and heatmap.png. Because this is a markdown skill file, the documentation should disclose that these examples create local files and may affect the user's workspace.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.