plan-epic
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The workflow instructs reading repo files (README.md, CLAUDE.md, AGENTS.md, package.json, and optional prototype folder markdown/HTML/image files) at runtime, which are outsider-authored if the repository content was not authored by the operator; that content would be ingested as free text into the agent context during the “Read the Repo” step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata