research-pipeline
Warn
Audited by Socket on Oct 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's research purpose matches its broad orchestration behavior, but its autonomy is unusually high and includes silent actions, direct experiment/code execution, optional repo-direct reviewer access, and acceptance of arbitrary base repos. No confirmed malware or credential theft path is shown, but the scope and unattended real-world actions make it a high operational-risk skill.
Confidence: 88%Severity: 72%
Audit Metadata