test-engineer
Warn
Audited by Snyk on Jul 5, 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). The skill reads outsider-authored free text from
<project>/.unity-review/report/(outputs ofreview-testing/review-hotspot), which are not authored by the operating user and are ingested as markdown into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata