agentos

Warn

Audited by Socket on Apr 29, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

Suspicious. The skill's purpose matches an autonomous agent framework, but its footprint is high-risk because it enables unattended agent actions and encourages loading additional unreviewed skills. Install provenance is same-project GitHub and not overtly deceptive, so this is not confirmed malware, but it is a materially risky framework skill.

Confidence: 85%Severity: 74%
Audit Metadata
Analyzed At
Apr 29, 2026, 06:16 AM
Package URL
pkg:socket/skills-sh/fikriaf%2Fagentos-skills%2Fagentos%2F@ca6a929cda0fe29089a9289dd7264413b1d17b88