mundi-orch-counterparty-enrich
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md step 6 (“Perplexity grounding”) indicates runtime ingestion of “recent news, press releases, context” via
mcp__perplexity__perplexity_research, which fetches public web content authored by outsiders and feeds it into the agent’s LLM context for grounding.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata