ClawHub
Back to skill

Security audit

Excel Spreadsheet

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently uses CellCog to generate spreadsheets, with routine external-service and dependency-installation considerations.

Treat prompts and supplied data as shared with CellCog; use only information you are authorized to send. Review the separate CellCog dependency and prefer pinned installation versions. Check generated formulas before relying on them. This review covers the supplied instructions, not the external SDK or service implementation.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The workflow sends task prompts to CellCog without warning that user-provided data is transmitted to a third-party service.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow submits task prompts to an external service without explicitly explaining the data-transfer boundary or requiring authorization before including sensitive information. Although CellCog's involvement is openly advertised and no covert exfiltration is evident, the financial, employee, and sales use cases increase the likelihood that prompts could contain confidential or personal data.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The installation command invokes an unpinned npm CLI through npx skills, potentially downloading and executing a release that has not been reviewed. A compromised upstream release could execute code with the agent user's permissions and access local files or credentials; however, the finding's characterization as an MCP server is inaccurate because this is an installation CLI.

Content

No source excerpt is available for this finding.