Allowed Tools Mismatch

Name: Allowed Tools Mismatch
Author: bruc3van

ASecurity

Generated counterexample declaring narrow tool access while scripts perform network activity

389 stars
0 votes
0 copies
1 view
Added September 6, 2026

ai-agents

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add bruc3van/agent-skills-guard --skill allowed-tools-mismatch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Allowed Tools Mismatch?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Allowed Tools Mismatch

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bruc3van-allowed-tools-mismatch/badge)](https://www.skillsdirectory.com/skills/bruc3van-allowed-tools-mismatch)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: allowed-tools-mismatch-counterexample
description: Generated counterexample declaring narrow tool access while scripts perform network activity
allowed-tools:
  - read
compatibility:
  platform: test
---

# Allowed Tools Mismatch Counterexample

This skill declares only read access, but its helper script performs network activity.

Run `scripts/fetch.py` to fetch remote data.