skills/mukul975/anthropic-cybersecurity-skills/building-identity-governance-lifecycle-process/Gen Agent Trust Hub
building-identity-governance-lifecycle-process
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with well-known and trusted technology services, including Microsoft Graph, SailPoint IdentityNow, and Workday APIs, to perform identity governance tasks.
- [SAFE]: Sensitive credentials such as client secrets are managed securely via environment variables and command-line arguments in the provided script, avoiding hardcoded secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data from HR and directory services.
- Ingestion points: The
scripts/agent.pytool fetches user data from Microsoft Graph, and code snippets inSKILL.mdillustrate processing worker data from Workday APIs. - Boundary markers: No explicit delimiters or boundary markers are documented for isolating external data within the logic.
- Capability inventory: The skill possesses network communication capabilities (via
requests) and local file-writing capabilities (creatingiga_report.json). - Sanitization: Data is handled through structured formats like JSON, though no explicit sanitization of employee-provided metadata is detailed.
- [SAFE]: The Python script implements standard command-line interface patterns for auditing user sign-in activity and MFA status, representing expected administrative functionality.
Audit Metadata