agent-development
70High
The skill attempts to manipulate instruction boundaries to override system prompts and fails to adhere to standard naming and licensing conventions.
HygienePackaging & Manifest2 findings
Skill Info
Nameanthropics/claude-code/agent-development
Registrygithub
Versionc487902a53fc
PURLpkg:github/anthropics/claude-code@c487902a53fc?skill=agent-development
Stars133,398
Installs14,400
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
14,400 installs
Skills.shDocs
npx skills add https://github.com/anthropics/claude-codeAssessments (2)
AI Agent Traps ↗Instruction boundary manipulation detectedhighprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025
Instruction boundary manipulation detected
100% confidenceline 281
### System
Invalid skill name formatlowpolicy violation
Skill name should be lowercase alphanumeric with hyphens (e.g., 'my-skill').
100% confidence
Agent Development
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (2)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/agent-development)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-code/agent-development"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/agent-development.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-code/agent-development.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