implement-factory
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text is ingested into the evaluation agent’s LLM context via
{all_scenario_content}, which is read from{specDirectory}/scenarios/{unit.id}/*.md(scenario files are not authored by the operating user at runtime and are treated as external spec content).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata