plan
Warn
Audited by Snyk on Jun 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: 0.75). The required workflow reads
.specs/prds/<slug>.md(PRD authored by an outsider) and then uses its free-form text to generate the plan that is fed into the agent’s LLM context, creating an indirect prompt-injection path via PRD body text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata