writing

Warn

Audited by Socket on Mar 26, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the core writing purpose is plausible, but the skill's actual footprint is much broader because it repeatedly delegates to many other skills, autonomously processes untrusted web content, writes extensive files, and runs shell tooling. The main concern is transitive trust and prompt-injection exposure, not confirmed malware or direct credential theft.

Confidence: 89%Severity: 76%
Audit Metadata
Analyzed At
Mar 26, 2026, 05:07 PM
Package URL
pkg:socket/skills-sh/K-Dense-AI%2Fclaude-scientific-skills%2Fwriting%2F@675b8e250348ef59a700d28d8482f1bf10299b39