skills/mukul975/anthropic-cybersecurity-skills/implementing-google-workspace-sso-configuration/Gen Agent Trust Hub
implementing-google-workspace-sso-configuration
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The utility script
scripts/process.pyis designed to fetch SAML metadata XML and check the reachability of Single Sign-On (SSO) endpoints using network requests.\n - Evidence: Uses the
requestslibrary to perform GET and HEAD requests to user-provided IdP URLs for validation purposes.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a potential surface for indirect prompt injection as it ingests and processes external data from SAML metadata, certificate files, and login logs.\n - Ingestion points: External URLs provided to the validator script in
scripts/process.py, and configuration/log file paths inscripts/agent.py.\n - Boundary markers: The skill does not implement explicit boundary markers or "ignore instructions" delimiters for the processed external data.\n
- Capability inventory: The skill has capabilities for network communication and file system operations (reading logs/configs and writing audit reports).\n
- Sanitization: Includes XML parsing validation via
lxmland basic HTTPS scheme checks for URLs.
Audit Metadata