skill-router
Warn
Audited by Snyk on Aug 17, 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). Source the attacker-authored free text is the user’s task/query passed into
scripts/skill_index.py search/context, which then causes the program to read and include localSKILL.mdbodies (potentially from third-party installed skill roots likeglobal/plugin) into the “skill context packet”.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata