deep-research

Warn

Audited by Socket on May 9, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The core research behavior is coherent with the stated purpose, but the skill carries elevated risk from transitive skill installation, third-party git-clone dependency instructions, and high-risk prompt-injection exposure created by combining untrusted web intake with write/task/browser capabilities. No clear credential harvesting or malicious exfiltration is shown, so this is not confirmed malware.

Confidence: 86%Severity: 74%
Audit Metadata
Analyzed At
May 9, 2026, 05:43 PM
Package URL
pkg:socket/skills-sh/mikeng-io%2Fagent-skills%2Fdeep-research%2F@00ae769e3c1fbbcee89aa6b1100e6e012ad90edb
Security Audit — socket — deep-research