coding-cli-management

Warn

Audited by Socket on Oct 21, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill is internally coherent for delegated coding-cli management, and the cited Qwen install sources appear official rather than deceptive. However, its footprint is high-risk by design: unattended auto-approve CLI execution, ambient credential inheritance, broad delegating-agent privileges, and automatic persistence of prompts/logs to shared storage. This looks more like a dangerous operations skill than credential-stealing malware.

Confidence: 90%Severity: 78%
Audit Metadata
Analyzed At
Oct 21, 2026, 04:30 PM
Package URL
pkg:socket/skills-sh/agentscope-ai%2Fagentteams%2Fcoding-cli-management%2F@1b5eba8900442bc15a4b31fbeebab1752cec143f