azure-appconfiguration-java

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to download the official Azure App Configuration client library (com.azure:azure-data-appconfiguration) and the Azure SDK Bill of Materials (BOM) from Maven Central. These packages are provided by a trusted organization.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from a remote Azure App Configuration store, which creates a surface for indirect prompt injection. If an attacker modifies configuration values to include malicious instructions, they could influence the agent's logic.
  • Ingestion points: Data is retrieved from the remote service using methods such as getConfigurationSetting, listConfigurationSettings, and listConfigurationSettingsForSnapshot as shown in SKILL.md.
  • Boundary markers: The provided code examples do not use delimiters or boundary markers to differentiate retrieved configuration values from internal instructions.
  • Capability inventory: The skill provides comprehensive capabilities to read, write, and list configuration settings, feature flags, and point-in-time snapshots.
  • Sanitization: No sanitization or validation of the retrieved configuration values is demonstrated in the provided code snippets before the data is used or printed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:23 PM