study-guide

Warn

Audited by Snyk on Feb 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's Step 1 "Gather sources" explicitly directs the agent to "Read files, fetch URLs, or accept pasted text" and to "Read every source completely before writing anything" (SKILL.md), so arbitrary public/untrusted webpages or pasted third‑party content would be ingested and directly drive the study‑guide generation and answers.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 22, 2026, 06:05 AM