skills/mukul975/anthropic-cybersecurity-skills/implementing-azure-defender-for-cloud/Gen Agent Trust Hub
implementing-azure-defender-for-cloud
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes telemetry and security findings from external Azure APIs, which is a standard attack surface for monitoring and auditing tools.
- Ingestion points: The
scripts/agent.pyscript retrieves data from Azure Security Center viaclient.assessments.list(),client.alerts.list(), andclient.regulatory_compliance_standards.list(). - Boundary markers: No explicit boundary markers or delimiters are used when displaying retrieved data or saving it to the JSON report.
- Capability inventory: The skill includes capabilities to write audit reports to local files using
json.dumpinscripts/agent.pyand execute Azure CLI commands for security configuration. - Sanitization: The skill does not perform explicit sanitization or filtering of text fields (such as assessment names or alert descriptions) retrieved from the cloud environment.
Audit Metadata