agent-development
70High
The skill attempts to manipulate instruction boundaries to override system prompts, posing a significant risk of unauthorized behavior and prompt injection.
HygienePackaging & Manifest1 finding
Skill Info
Nameanthropics/claude-plugins-official/agent-development
Registrygithub
Version315339817c4e
PURLpkg:github/anthropics/claude-plugins-official@315339817c4e?skill=agent-development
Stars31,307
Installs4,000
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
4,000 installs
Skills.shDocs
npx skills add https://github.com/anthropics/claude-plugins-officialAssessments (2)
AI Agent Traps ↗Instruction boundary manipulation detectedhighinstruction boundaryAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025
Instruction boundary manipulation detected
95% confidenceline 142
## System Prompt Design The markdown body becomes the agent's system prompt
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-plugins-official/agent-development)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-plugins-official/agent-development"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-plugins-official/agent-development.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-plugins-official/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