forge
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). Yes: in
references/specify.mdthespecifyphase may useWebSearch/WebFetchand then reads and summarizes fetched pages as “External References,” which is outsider-authored free text that can be incorporated into the agent’s LLM context during runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata