self-improvement

Warn

Audited by Socket on Feb 28, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

Benign: The code fragment describes a self-improvement logging skill that writes to local .learnings markdown files and promotes certain learnings within project memory. It does not perform network calls, read credentials, or execute external binaries by itself (aside from references to local hook scripts). The data flows and access are proportionate to its purpose and maintain a clear boundary around data locality and governance. Overall security risk is low, with no malware indicators detected.

Confidence: 75%Severity: 75%
Audit Metadata
Analyzed At
Feb 28, 2026, 03:31 AM
Package URL
pkg:socket/skills-sh/hanzoskill%2Fself-improving-agent%2Fself-improvement%2F@819fde972d0d7b0a39f4ea8315d222e3ffd528af