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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata