recipe-modularization-audit-plan-marshall-skills
Warn
Audited by Snyk on Jul 11, 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). Yes: the required workflow gathers a user-chosen
{target_root}viaAskUserQuestionand then reads everySKILL.md/sub-.mdunder that tree in full (Step 2), so any outsider-authored markdown in that path becomes free text in the agent’s LLM context during the audit.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata