ClawHub
Back to skill

Security audit

Excel

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only Excel helper that gives spreadsheet formulas, pivot-table steps, and cautious VBA guidance without requesting execution rights or persistence.

Installers should understand that the skill may generate VBA macro code when users ask for automation; review any macro before running it in Excel and provide workbook/platform details so the assistant can choose safer formulas or pivot tables when they fit.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase "solve excel problem" is broad enough to match many ordinary spreadsheet requests, which can cause the skill to activate outside a clearly intended invocation context. Over-broad activation increases the chance of prompt-routing mistakes, unexpected skill selection, and accidental exposure of users to the skill's guidance when another tool or narrower skill would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase "build pivot table" is ambiguous because it resembles a common user request rather than a deliberate invocation of this specific skill. This can create routing collisions with general assistance flows and may invoke the skill when the user did not intend to use a specialized diagnostic engine.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrase "write vba macro" is highly generic and likely to appear in ordinary help requests, making unintended activation plausible. In a skill that can generate automation scripts, broad matching is more sensitive because it may steer users into macro-generation workflows without an explicit, scoped request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.