skills/adird/agent-shell-hamelech/babysit/Snyk

babysit

Warn

Audited by Snyk on Aug 10, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The skill requires reading PR review thread comment bodies during each iteration (Step 3 “Comments: … read only the comment body”), and those comments can be authored by outsiders, creating an indirect prompt-injection exposure.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Aug 10, 2026, 06:20 AM

Issues

1