ClawHub
Back to skill

Security audit

Sheet Data Enrichment

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed spreadsheet enrichment helper that fetches linked sources and writes verified results back to sheets.

Before installing, be aware that this skill may read spreadsheet contents, visit URLs from the sheet, use browser automation for difficult pages, and write results back. Use it when you intend that workflow, and review the proposed source and target columns before approving batch updates.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises very broad trigger phrases like 'fill in', 'complete the table', 'summarize by', and generic spreadsheet enrichment terms, which can cause it to activate for routine spreadsheet tasks beyond its intended scope. Because this skill fetches external URLs/APIs and writes back to sheets, over-triggering increases the chance of unintended external access, data exfiltration, or unsafe modification of user data in contexts where a simpler local-only spreadsheet skill should have been used.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file includes a dedicated 'Chinese Media' section with Chinese trigger markers and examples, but does not clarify that these patterns are optional or context-specific. Under the policy rule, locale-specific handling can be a concern when a skill appears to force a language or locale choice without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.