litbase
Warn
Audited by Snyk on Sep 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow reads paper metadata and search queries from Semantic Scholar via API calls (
commands/feed.md,commands/read.md), which returns outsider-authored paper abstracts, titles, and author names into the agent's runtime context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata