prompt-engineering-patterns
The skill is vulnerable to prompt injection through dynamically fetched external data files that can override system instructions and manipulate the agent's execution flow.
Skill Info
Install
Assessments (2)
AI Agent Traps ↗Instruction boundary manipulation detected
### Instruction
The skill encourages the use of external data files like 'assets/few-shot-examples.json'. If these files are dynamically fetched or user-provided, they could contain malicious instructions that the agent will execute as part of its few-shot learning process.
assets/few-shot-examples.json
Skill does not specify a license field. Specifying a license helps users understand usage terms.
Badge
[](https://mondoo.com/ai-agent-security/skills/github/sickn33/antigravity-awesome-skills/prompt-engineering-patterns)<a href="https://mondoo.com/ai-agent-security/skills/github/sickn33/antigravity-awesome-skills/prompt-engineering-patterns"><img src="https://mondoo.com/ai-agent-security/api/badge/github/sickn33/antigravity-awesome-skills/prompt-engineering-patterns.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/sickn33/antigravity-awesome-skills/prompt-engineering-patterns.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