clade-embeddings-search
Warn
Audited by Socket on Aug 21, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's stated purpose mostly matches its content, and its documented API flow points to Anthropic's official endpoints. The main concern is internal inconsistency in the TypeScript package name (`@claude-ai/sdk` vs official `@anthropic-ai/sdk`) combined with broad `Bash(npm:*)` permissions, which creates avoidable supply-chain and execution risk for a guide-style skill.
Confidence: 89%Severity: 56%
Audit Metadata