ClawHub
Back to skill

Security audit

excel-data-cleaner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward spreadsheet cleaning helper that reads user-provided Excel or CSV files and writes cleaned outputs and reports, with no evidence of hidden or unrelated behavior.

Before installing, be aware that the skill may create output spreadsheets and reports from files you provide. Choose output paths deliberately, keep originals backed up, and review the cleaning strategy before allowing row deletion, outlier clipping, or missing-value filling.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill explicitly instructs writing cleaned spreadsheets and Markdown reports but declares no tool scope such as permissions or allowed-tools. That creates a mismatch between documented behavior and enforced capability boundaries, increasing the chance an agent can perform unintended file writes or invoke broader tools than necessary. In this context the writes are part of the intended workflow, so the issue is not inherently malicious, but it is still a real security control gap.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description includes the trigger phrase '这份表帮我整理分析一下', which is a broad, natural request that could match many spreadsheet-related conversations beyond this specific skill. The file does not provide exclusion conditions or negative examples to narrow when this skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.