exploring-mcp-sessions
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill’s required runtime path uses the typed tool
posthog:mcp-analytics-sessions-generate-intentto have an LLM summarise and return a prose “intent” derived from recorded$mcp_intentvalues (which originate from the MCP client/harness messages, i.e., outsider-authored free text), so that free text is ingested by the LLM during summarisation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata