heal-spec
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill reads outsider-authored free text from
failure.jsonandfailure.htmlin the runtimeoutput-dir(e.g.,./output/failure.json/./output/failure.html), which are generated from a failing demo run and can include arbitrary page DOM/text not authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata