skills/sickn33/agentic-awesome-skills/iterate-pr/Socket

iterate-pr

Warn

Audited by Socket on Aug 25, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill’s purpose matches its GitHub/CI capabilities and official tool usage, so it is not overtly malicious, but it grants an agent high-impact autonomy: reading untrusted PR content, changing code, pushing commits, and posting replies in a loop. Main risk is autonomous external action plus indirect prompt-injection from PR feedback/logs, not credential theft or deceptive data routing.

Confidence: 90%Severity: 76%

Audit Metadata

Analyzed At

Aug 25, 2026, 06:24 AM

Package URL

pkg:socket/skills-sh/sickn33%2Fagentic-awesome-skills%2Fiterate-pr%2F@0691e31eec681737da7b1effd4c4d953c41ee7a35d37d680ce42cc0d5496390e