mongodb-atlas-stream-processing
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official MongoDB Atlas Stream Processing examples repository (https://github.com/mongodb/ASP_example) for fetching validated pipeline patterns and quickstarts.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process untrusted data from various external sources.
- Ingestion points: Processes data from Kafka topics, MongoDB collections, Kinesis streams, S3 buckets, and external HTTPS APIs through
$source,$lookup, and$httpsstages. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the data content itself.
- Capability inventory: The skill utilizes MCP tools to provision workspaces, create connections, and deploy/manage streaming processors.
- Sanitization: Recommends the use of the
$validatestage for schema enforcement to filter or redirect invalid data to a Dead Letter Queue (DLQ).
Audit Metadata