AGENT LAB: SKILLS

open-prose

Fail

Audited by Socket on Feb 15, 2026

1 alert found:

Malware
MalwareHIGH
SKILL.md

The OpenProse skill fragment is coherent and purpose-aligned, enabling VM-like execution and multi-agent orchestration with remote program support. Primary security risks arise from executing untrusted remote code; mitigate with provenance verification, sandbox execution, prompt-based confirmations, and strict logging controls. No evidence of hardcoded secrets or backdoors in this fragment.

Confidence: 68%Severity: 60%
Audit Metadata
Analyzed At
Feb 15, 2026, 08:01 PM
Package URL
pkg:socket/skills-sh/openprose%2Fprose%2Fopen-prose%2F@ad6ecc513a1b77010ee620a4b0632dbf4ba762eb