webgpt-review
Warn
Audited by Snyk on Aug 26, 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). In
skills/webgpt-review/scripts/run-webgpt-review.sh, the caller-provided--bundlefile contents are read and submitted via the../ask/run.sh webgpt-review --bundle ...command, so outsider-authored review text can directly reach the LLM at runtime without selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata