harness-plan
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill.md’s Step 4 “planner-interview” injects
{{USER_REQUEST}}(raw user input that started/harness-plan) into the Planner sub-agent prompt, meaning outsider-authored free text directly reaches the LLM during required runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata