skills/mukul975/anthropic-cybersecurity-skills/implementing-zero-trust-network-access-with-zscaler/Gen Agent Trust Hub
implementing-zero-trust-network-access-with-zscaler
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a potential surface for indirect prompt injection if an agent processes the resulting reports.
- Ingestion points:
scripts/agent.pyreads JSON responses from the Zscaler ZPA API;scripts/process.pyreads local JSON and CSV files via command-line arguments. - Boundary markers: None identified in the provided instructions or script logic to delimit external content.
- Capability inventory: File system write access (report generation), network connectivity testing (TCP/TLS checks), and authenticated API requests to Zscaler services.
- Sanitization: No explicit sanitization or validation of the content of the API responses or CSV/JSON fields before they are included in generated reports or printed to the console.
Audit Metadata