ClawHub
Back to skill

Security audit

Df Merger

Security checks for vulnerabilities and agentic risk

Overview

This skill is a construction DataFrame merging helper with a slightly broad activation phrase but no hidden execution, persistence, or unrelated data access.

Install this if you want help merging construction-related datasets. Be aware that its trigger wording is broader than necessary, so use it for explicit data merging or cleanup tasks and avoid handing it unrelated project-management materials unless you intend them to be processed.

A.I.G

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

SkillSpector

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 instruction 'When the user asks to assist with construction project tasks' is much broader than the skill's stated purpose of merging pandas DataFrames from construction sources. This can cause the skill to activate for general construction-management requests and then steer the agent into using SKILL.md methods or data-handling flows outside the user's actual need, increasing the chance of inappropriate tool use, data over-collection, or unintended workflow execution.

Static analysis

No suspicious patterns detected.