agent-ai-engineer
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's install_command fetches and writes the agent instruction file from https://raw.githubusercontent.com/majiayu000/claude-skill-registry-data/main/data/agent-ai-engineer/SKILL.md, which will directly control the agent's prompts/instructions at runtime.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata