skills/laststance/skills/qa-team/Socket

qa-team

Warn

Audited by Socket on May 19, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS. The core QA purpose is coherent, but the skill expands trust to ambiguous external skills and MCP tool namespaces without clear provenance or pinning. There is no direct credential theft or obvious exfiltration path in the text, yet the transitive-skill and external-tool trust chain makes the overall execution risk medium-high for an AI agent skill.

Confidence: 86%Severity: 74%

Audit Metadata

Analyzed At

May 19, 2026, 12:57 AM

Package URL

pkg:socket/skills-sh/laststance%2Fskills%2Fqa-team%2F@f0f0f701358176974f89883e8ec320e3c794a16e