coderabbit
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: 0.90). The skill's Workflow and references explicitly fetch and parse GitHub PR review threads and review bodies via GraphQL and REST (see "Fetch CodeRabbit Review Threads" in Workflow step 2 and references/graphql-queries.md, plus reading code at referenced file/line in step 4), which ingests user-generated, untrusted PR comments and code that the agent must interpret and act on — allowing indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata