eu-ai-act-triage-en
Warn
Audited by Snyk on Jul 14, 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). SKILL.md Step 0 requires fetching the current Regulation (EU) 2024/1689 text from EUR-Lex (public web content) or via the
mcp-eu-complianceconnector, which would ingest outsider-authored free text (the regulation’s wording) into the LLM context for in-session verification.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata