coding-quality-loop
The skill is vulnerable to prompt injection because it dynamically loads and executes instructions from external markdown files that can be manipulated by an attacker.
Skill Info
Install
npx skills add https://github.com/zaingz/coding-quality-loopAssessments (2)
AI Agent Traps ↗The skill instructs the agent to load external markdown files (`references/*.md`) on demand. If these files are modified by an attacker, they can inject instructions into the agent's reasoning process. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
Load references/ only when needed.
NER model detected organization in skill content (confidence: 0.75)
D****
NER model detected organization in skill content (confidence: 1.00)
M**
Version History (3)
Badge
[](https://mondoo.com/ai-agent-security/skills/github/zaingz/coding-quality-loop)<a href="https://mondoo.com/ai-agent-security/skills/github/zaingz/coding-quality-loop"><img src="https://mondoo.com/ai-agent-security/api/badge/github/zaingz/coding-quality-loop.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/zaingz/coding-quality-loop.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