api-security-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Azure Resource Graph results and API Management policy XML files. Maliciously crafted configuration metadata or policy comments could potentially influence agent behavior by embedding instructions within the data being analyzed.\n- Ingestion points: The skill ingests data from Azure Resource Graph query results and API Management policy definitions (XML format).\n- Boundary markers: The instructions do not specify the use of delimiters or explicit warnings for the agent to ignore instructions embedded within the analyzed data content.\n- Capability inventory: The skill utilizes Azure Resource Graph queries to inspect environment state and SKU details.\n- Sanitization: No sanitization, escaping, or schema validation is performed on the ingested policy content or resource metadata before it is processed by the agent.
Audit Metadata