falsification-first-audit

Warn

Audited by Socket on Sep 24, 2026

1 alert found:

Anomaly
AnomalyLOW
SKILL.md

SUSPICIOUS. The skill’s stated purpose is coherent and the artifact itself contains no direct malware patterns, credential harvesting, or exfiltration. The risk comes from mandatory transitive loading of multiple unpinned sub-skills—especially execute-probe—whose provenance and behavior cannot be verified from this artifact, making the trust boundary broader than the visible content.

Confidence: 88%Severity: 58%
Audit Metadata
Analyzed At
Sep 24, 2026, 03:10 AM
Package URL
pkg:socket/skills-sh/yogsoth-ai%2Fde-anthropocentric-research-engine%2Ffalsification-first-audit%2F@9e89fbd84f6837356b0454859120cdcbb69102f37d37cd3e4893330464f5b153