ISBN Book Number Query - ISBN图书书号查询

• Outcome: Review
• Latest audit: May 29, 2026, 9:31 PM
• Version:
  1.0.5

Overview

This is a disclosed code-review helper, but it defaults to broad full-access review execution and may send code diffs to external reviewer CLIs.

Review the skill before installing in sensitive repositories. Use `--no-yolo` and `--fallback-reviewer none` when you want sandbox prompts and no automatic third-party model fallback, and avoid using it on private code unless those reviewer CLIs and their data handling are acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill metadata declares required binaries and environment variables, and the skill clearly relies on outbound API access, but it does not explicitly declare permissions for network and secret/environment access. This weakens least-privilege enforcement and can cause the runtime or reviewers to underestimate the skill's capability to transmit user-supplied queries and use an API key externally.

VirusTotal

66/66 vendors flagged this skill as clean.