field-dev-code-recon
Warn
Audited by Socket on Apr 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's purpose mostly matches its capabilities, and there is no suspicious installer or third-party credential routing. However, it combines untrusted external content ingestion with write access, GitHub issue creation, and git push, enabling indirect prompt injection and autonomous public/repo-affecting actions beyond a low-risk research skill.
Confidence: 88%Severity: 74%
Audit Metadata