github

Warn

Audited by Snyk on Mar 6, 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). The workflow (references/stacked-pr-workflow.md) explicitly instructs the agent to "Fetch PR details to map the chain" and to use the gh CLI to read and edit GitHub PRs, meaning the agent will ingest user-generated content from public GitHub which can influence rebase/merge actions and commit titles.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 05:37 AM