creating-skills
Warn
Audited by Snyk on Aug 8, 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). The required runtime workflow that reads outsider-authored free text is the eval-review viewer generator, which ingests task prompts and run artifacts from workspace files (e.g., eval_metadata.json/transcript.md and outputs/*.txt/.md/.json/.csv/.py/etc.) into embedded HTML for review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata