ClawHub
Back to skill

Security audit

Sheetsmith

Security checks for vulnerabilities and agentic risk

Overview

Sheetsmith is a straightforward spreadsheet helper whose file reading and writing behavior is disclosed and aligned with its purpose.

Install only if you are comfortable letting the agent process spreadsheet files you point it at. Prefer --output for edits, keep backups before using --inplace, review pandas query or transform expressions before running them, and do not share confidential or regulated data through personal messaging channels unless your policy allows it.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README explicitly states that modified spreadsheet files can be sent back via Telegram or WhatsApp, but it does not warn that these platforms may expose sensitive data to third parties, retain copies, or violate organizational data-handling rules. In a data-processing skill that handles arbitrary CSV/Excel attachments, normalizing outbound sharing without a privacy warning can lead users to transmit confidential or regulated information over insecure or non-approved channels.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises and operationalizes shell execution and file-writing behavior through its CLI workflow, but the manifest declares no explicit tool scope or permissions boundaries. That creates an authorization gap: an agent may invoke a skill that can read arbitrary spreadsheet paths and overwrite or create files without any machine-readable restriction, increasing the chance of unintended file modification or broader command execution through the skill wrapper.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_sheetsmith.py (reported line 14)May include surrounding context.

python
def run_cli(args, workspace):
    return subprocess.run(
        [sys.executable, str(SCRIPT_PATH)] + args,
        capture_output=True,
        text=True,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file documents an --inplace mode that overwrites files, which can affect user data. While the usage notes mention when overwrite occurs, they do not explicitly warn that the operation is destructive or recommend backing up data before using it.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/sheetsmith.py:123