interactive
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). Source:
/interactive(SKILL.md) routes by inspecting the user’s current conversation for an installed technique and then loads the selected canonicalSKILL.md, meaning outsider free text is ingested at least for method selection/routing but no external item-search/read is described in this required workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata