translation-audit
Warn
Audited by Snyk on Jun 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: 0.65). Outsider free text can enter the LLM context via web search glossary resolution (Layer 2 → Glossary resolve tier L3) when
--web-searchis ON: the skill fetches public web pages and ingests their readable text to propose glossary mappings, which then feed the LLM judge/proposal prompts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata