azure-eventhub-rust
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
cargo addto installazure_messaging_eventhubs,azure_identity, andazure_core. These are official, well-known libraries managed by the Azure/Microsoft organization and hosted on the standard crates.io registry. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external event data, which inherently creates an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context via the
receiver.stream_events()method inSKILL.md. - Boundary markers: The documentation includes instructions to process events safely and explicitly warns against logging raw payloads.
- Capability inventory: The skill does not include any dangerous capabilities such as shell command execution, dynamic code evaluation, or arbitrary file system writes.
- Sanitization: While specific sanitization code is not provided in the snippets, the reliance on Rust's type system and the explicit best practice instructions mitigate common risks.
Audit Metadata