azure-cosmos-db

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a documentation-oriented assistant that facilitates access to Azure Cosmos DB resources.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from learn.microsoft.com and references official code samples from github.com/azure and github.com/azure-samples. These sources are well-known, official, and trusted for the purpose of technical documentation.
  • [COMMAND_EXECUTION]: No shell commands, scripts, or executable files are provided or invoked by the skill.
  • [DATA_EXFILTRATION]: There is no access to local sensitive files, environment variables, or credentials. Network operations are limited to retrieving documentation from official sources.
  • [PROMPT_INJECTION]: Instructions are focused on navigating the documentation index and do not contain patterns for bypassing safety filters or overriding system instructions.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external documentation at runtime, the sources are trusted official Microsoft domains, and the skill lacks the capabilities (like file writing or shell access) to be leveraged in an attack chain.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:10 PM
Security Audit — agent-trust-hub — azure-cosmos-db