azure-appconfiguration-java

Fail

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill defines Java code patterns that create a significant indirect prompt injection surface by combining data ingestion with high-privilege write capabilities.\n
  • Ingestion points: Configuration data is ingested via client.getConfigurationSetting and client.listConfigurationSettings as shown in references/acceptance-criteria.md.\n
  • Boundary markers: None present. The code snippets demonstrate direct processing of strings retrieved from the external service.\n
  • Capability inventory: The skill provides patterns for addConfigurationSetting, setConfigurationSetting, and deleteConfigurationSetting, allowing the agent to modify the external environment.\n
  • Sanitization: No sanitization or validation logic is present in the provided snippets to mitigate the risk of malicious configuration values.\n- [External Downloads] (LOW): The skill references the com.azure:azure-data-appconfiguration Maven package.\n
  • Evidence: Reference to Azure SDK for Java repository and package names.\n
  • Trust Status: The azure organization is a trusted source, which downgrades this dependency finding to LOW per trust-scope rules.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 14, 2026, 04:59 PM