Back to skill

Security audit

Join Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill is low-risk but appears inaccurately documented: it says it performs SQL-like joins, while the included script only concatenates matching line numbers from two files.

Install only if you understand this does not currently implement a real join-tool as documented. It should be corrected to either implement field-based joins or describe itself as a simple two-file line concatenator.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description promises SQL-like joining of text files using a common field. The code does not parse fields, compare keys, or implement any join behavior. It simply reads two files and concatenates each pair of lines at the same index. This is a materially different primary purpose from a field-based relational join, so the description does not accurately represent the code's behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest describes relational-style joins based on a common field across multiple files. The code only reads exactly two files and zips them line-by-line, printing concatenated lines without parsing fields or matching on any key, which is a substantive mismatch in behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.