100Critical
The skill attempts to override system instructions and performs unauthorized network and file operations without declaring necessary tool permissions, posing a significant security risk for arbitrary code execution.
HygienePackaging & Manifest1 finding
Skill Info
Nameanthropics/claude-for-legal/skills-qa
Registrygithub
Version5ceb305b30b4
PURLpkg:github/anthropics/claude-for-legal@5ceb305b30b4?skill=skills-qa
Stars8,549
Installs259
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
259 installs
Skills.shDocs
npx skills add https://github.com/anthropics/claude-for-legalAssessments (3)
AI Agent Traps ↗Role/instruction override attempt detectedcriticalprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025
Role/instruction override attempt detected (seen 2 times in this file at lines 115, 441)
95% confidenceline 115
ignore previous instructions
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-for-legal/skills-qa)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-for-legal/skills-qa"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-for-legal/skills-qa.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-for-legal/skills-qa.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet, discover and control Shadow AI usage.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow