skills/mukul975/anthropic-cybersecurity-skills/performing-entitlement-review-with-sailpoint-iiq/Gen Agent Trust Hub
performing-entitlement-review-with-sailpoint-iiq
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard Identity Governance and Administration (IGA) workflows for SailPoint IdentityIQ. The documentation provides clear examples for configuring compliance campaigns and SOD policies.
- [SAFE]: The Python agent (
scripts/agent.py) is a well-structured API wrapper that utilizes therequestslibrary for communication with the SailPoint backend. It correctly handles authentication via user-provided command-line arguments and does not contain hardcoded credentials or malicious network operations. - [SAFE]: The BeanShell code snippets provided in
SKILL.mdare for documentation and configuration purposes within the IdentityIQ platform and are not executed by the agent script or the skill environment itself. - [SAFE]: Indirect prompt injection surface is minimal. While the agent ingests data from the SailPoint API, it serves primarily to report and automate administrative tasks without piping untrusted data into sensitive execution contexts.
- Ingestion points:
agent.py(viaget_certifications,get_identities,get_entitlements, etc.) - Boundary markers: None (outputs raw JSON data to the console)
- Capability inventory: Network operations (REST/SCIM API calls) via the
requestslibrary inagent.py - Sanitization: Uses standard JSON serialization (
json.dumps) for output.
Audit Metadata