curate-collection

Warn

Audited by Snyk on Mar 18, 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). This skill's required workflow (Step 3 and Step 5 of SKILL.md) explicitly instructs the agent to use external public sources — e.g., Goodreads, LibraryThing, NoveList, HathiTrust/Internet Archive and other review sites — whose user-generated or publicly-sourced content the agent must read and interpret to make acquisition/reader-advisory decisions, creating a pathway for indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 07:14 AM
Issues
1