curate-language
Warn
Audited by Snyk on Jul 30, 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 skill curates and updates the consuming project’s glossary by ingesting the conversation-provided
$ARGUMENTSand repository artifacts (e.g.,AGENTS.md,CLAUDE.md,.claude/rules, and the nearest domain-vocabulary/context-map files) at runtime, so outsider-authored free text can be posted into the conversation/inputs that the workflow uses to decide what to write.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata