moonshot

Warn

Audited by Snyk on Mar 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md "Deep Immersion" step explicitly instructs the agent to "Read the backlog (GitHub issues, .groom/BACKLOG.md)," which requires ingesting user-generated, potentially public GitHub issues (untrusted third-party content) that the agent must read and use to choose the moonshot, enabling indirect prompt injection risk.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 12:45 AM
Issues
1