Skills
Navigate
skills/sickn33/agentic-awesome-skills/azure-cosmos-rust/Gen Agent Trust Hub

azure-cosmos-rust

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates reading data from Azure Cosmos DB containers using the read_item method. This creates a potential surface for indirect prompt injection if the stored database content contains malicious instructions intended for an agent. 1. Ingestion points: container.read_item in SKILL.md. 2. Boundary markers: None specified for the data payload. 3. Capability inventory: Azure Cosmos DB CRUD operations (create, read, replace, patch, delete). 4. Sanitization: The use of strongly-typed Rust structs for deserialization (into_model()) provides structural validation of the data.
  • [EXTERNAL_DOWNLOADS]: The skill references the official azure_data_cosmos and azure_identity crates for installation via cargo. These are official packages maintained by the Azure SDK team, which is a trusted organization, and are hosted on the standard crates.io registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 01:14 AM