ClawHub
Back to skill

Security audit

spreadsheet-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed spreadsheet-analysis connector that locally extracts spreadsheet text and sends it to a hosted analysis API when the user asks.

Install only if you are comfortable sending extracted spreadsheet cell text, filenames, and row locations to the AI Skills platform. Do not use it on confidential spreadsheets unless you have authorization, and protect the configured API key because it may be reused by related platform skills.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation expands the skill’s effective behavior beyond the stated spreadsheet analysis/Q&A/comparison scope by including export operations and asynchronous polling to a hosted external API. This matters because it signals additional data flows and remote execution dependencies that may expose spreadsheet contents, metadata, or derived outputs to a third-party service without being clearly reflected in the skill’s declared purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file's title and usage instructions are entirely in Chinese, which imposes a specific language on users without any visible opt-in or explanation. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all operational descriptions only in Chinese, which can force a specific language on users without opt-in. The policy explicitly calls for flagging language or locale constraints unless the skill offers a choice or clearly documents a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code emits user-facing errors and usage text in Chinese, such as the limit error and usage message, and continues this pattern throughout the script. The file does not offer locale selection or document that the skill is intentionally region-specific, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.