zscaler-zdx
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from Zscaler API endpoints such as applications, events, and alerts, which could contain instructions or malicious content provided by external sources.
- Ingestion points: list_zdx_applications, list_zdx_events, and list_zdx_alerts defined in SKILL.md.
- Boundary markers: No delimiters or ignore-instructions warnings are present in the tool definitions to isolate external data.
- Capability inventory: The skill provides read-only monitoring and analysis tools; no file system write, arbitrary shell execution, or outgoing network request capabilities (outside the MCP server) are visible.
- Sanitization: No sanitization or data validation steps are described in the instructions to handle potentially adversarial content from the Zscaler API.
Audit Metadata