The skill is vulnerable to dependency confusion attacks and prompt injection via unverified external references, while lacking secure instruction boundaries to prevent unauthorized agent behavior modification.
Instruction boundary manipulation detected
### System
The skill relies heavily on external reference files (e.g., references/architecture_patterns.md) to guide agent behavior; if these files are dynamically updated or fetched, they could be used to inject malicious instructions into the agent's reasoning process.
references/architecture_patterns.md
The 'Development Workflow' encourages running 'pip install -r requirements.txt' without specifying version pinning or hash verification, exposing the user to dependency confusion or malicious package injection.
pip install -r requirements.txt
Skill does not specify a license field. Specifying a license helps users understand usage terms.
[](https://mondoo.com/ai-agent-security/skills/github/sickn33/antigravity-awesome-skills/senior-architect)<a href="https://mondoo.com/ai-agent-security/skills/github/sickn33/antigravity-awesome-skills/senior-architect"><img src="https://mondoo.com/ai-agent-security/api/badge/github/sickn33/antigravity-awesome-skills/senior-architect.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/sickn33/antigravity-awesome-skills/senior-architect.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.