ClawHub
Back to skill

Security audit

Excel/CSV Master

Security checks for vulnerabilities and agentic risk

Overview

The skill is a spreadsheet helper with no hidden code, but it encourages automatic cleanup of important business data without enough safeguards.

Review this skill carefully before installing if you use it on financial, HR, customer, or operational spreadsheets. Work on copies, ask the agent to show row and column change counts before applying changes, and require explicit confirmation before deletions, deduplication, missing-value filling, outlier filtering, or saving results over existing files.

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
  • 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
Confidence
85% confidence
Finding
The skill title, description body, and all usage examples are presented in Chinese, with no indication that users may interact in another language or that the skill is intentionally limited to a Chinese-speaking region. This can violate language/locale policy when a skill imposes a language without user opt-in.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises automatic cleaning actions such as fixing formats and filling missing values without clearly warning that these operations can change source data semantics or cause irreversible loss if applied directly to original files. In a spreadsheet-processing skill, users may trust automation and unintentionally corrupt business, financial, or HR datasets through silent modification.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The examples explicitly include destructive operations like dropna() and drop_duplicates(), and later examples save output files without any backup or overwrite warning. These patterns can permanently remove records or replace expected outputs, which is risky in a skill aimed at non-technical office users handling important operational data.

Static analysis

No suspicious patterns detected.