Expertpack Export

• Outcome: Review
• Latest audit: May 29, 2026 at 9:32 PM UTC
• Version:
  1.1.0

Overview

This is a coherent export tool, but it should be reviewed because it scans sensitive agent/workspace knowledge and overstates its automatic redaction and formatting guarantees.

Install only if you are comfortable letting it inspect an OpenClaw workspace and create portable exports. Review the scan manifest and every generated file before sharing or syncing the export, especially files derived from user profiles, memory, logs, tools, infrastructure, and integrations. Do not rely on the advertised automatic redaction as complete.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill instructs the agent to read from the live workspace and write exported content, but it declares no explicit permissions. That mismatch weakens the trust boundary for operators and automated policy systems, because the skill can access and emit potentially sensitive workspace data without transparent capability declaration. In this context, the export function inherently touches broad agent state, so undeclared file access is more dangerous than in a narrowly scoped utility.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The skill description promises a safe, structured export with distillation, secret stripping, and Obsidian-compatible frontmatter, but the analyzed behavior reportedly diverges in multiple security-relevant ways. A description-behavior mismatch is dangerous because users may rely on claimed redaction, validation, and formatting guarantees when exporting sensitive knowledge; if those guarantees are incomplete or false, secrets or private data may be copied into portable artifacts and shared inadvertently. In an export/migration skill, this context amplifies risk because the whole purpose is to collect and package accumulated knowledge for movement elsewhere.

VirusTotal

67/67 vendors flagged this skill as clean.