find-skills

Warn

Audited by Socket on Sep 23, 2026

2 alerts found:

SecurityAnomaly
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill’s stated purpose matches its behavior, but that behavior is inherently high-risk because it installs additional skills from an open ecosystem and extends trust to unreviewed third-party content. The npm package provenance is reasonably legitimate, so this is not confirmed malware, but the transitive-install model, broad allowed source types, and alternate registry domain make it a high security-risk skill.

Confidence: 93%Severity: 84%
AnomalyLOW
scripts/agentteams-find-skill.sh

No clear malicious behavior is present in the script itself. The principal risks are runtime execution of an unpinned npm package via `npx -y`, global non-interactive installation of externally sourced skills, and transmission/exposure of authentication credentials through configurable endpoints and process arguments. These are significant supply-chain and credential-handling concerns, but they are consistent with the stated registry-wrapper purpose.

Confidence: 96%Severity: 62%
Audit Metadata
Analyzed At
Sep 23, 2026, 02:47 PM
Package URL
pkg:socket/skills-sh/agentscope-ai%2Fagentteams%2Ffind-skills%2F@c9b05d482e97b9f64168bdcc87b56edacafaca3c66422013c95d648119d9d9b2