meta-theory

Warn

Audited by Snyk on Apr 7, 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's Type D workflow and Agent Dispatch Protocol explicitly call for external source verification (e.g., "External source verification (GitHub repos, URLs, claims) → meta-scout") and use findskill/Specialist-ecosystem discovery, meaning agents will fetch and interpret public third‑party content (GitHub/URLs/Skills.sh) which can influence review ratings and follow-up actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 01:14 PM
Issues
1