stack
Warn
Audited by Socket on Oct 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The workflow is coherent for stacked PR management and includes meaningful safety rules, but its core dependency is a custom local `stack` executable with unverifiable provenance in the provided evidence. That black-box CLI can mutate local Git state and GitHub PRs, so the skill carries high security risk despite low evidence of malicious intent.
Confidence: 82%Severity: 76%
Audit Metadata