evolve

Warn

Audited by Socket on Apr 5, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS due to high operational risk, not clear malware. The skill’s purpose matches its capabilities, but it grants an agent broad autonomous write/exec authority, delegates to multiple other skills, processes potentially untrusted repo content, and can commit/push changes without per-action confirmation.

Confidence: 88%Severity: 78%
Audit Metadata
Analyzed At
Apr 5, 2026, 11:04 PM
Package URL
pkg:socket/skills-sh/boshu2%2Fagentops%2Fevolve%2F@c8d2bb062f108db8334049fc5d81fc97cf787173