software-factory-mode-2026hashi
Warn
Audited by Socket on Oct 21, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is mostly coherent as a PR workflow accelerator, but it deliberately removes approval guardrails and enables autonomous pushes, public review comments, and PR state changes. No strong exfiltration or malicious install behavior is evident in this fragment, but the autonomy scope is high for an agent skill.
Confidence: 88%Severity: 74%
Audit Metadata