didit-verification-management
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python scripts such as 'scripts/create_session.py', 'scripts/manage_workflows.py', and 'scripts/setup_account.py' that perform network requests to manage identity verification processes.
- [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's domains ('didit.me') and payment services ('stripe.com') to provide verification and billing functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes verification results and user metadata, which are external data sources.
- Ingestion points: Data retrieved from 'https://verification.didit.me/v3/session/{sessionId}/decision/' in 'SKILL.md' and 'scripts/create_session.py'.
- Boundary markers: None explicitly defined in the provided instructions to isolate untrusted data.
- Capability inventory: Network operations (GET, POST, PATCH, DELETE) implemented in 'scripts/create_session.py', 'scripts/manage_workflows.py', and 'scripts/setup_account.py'.
- Sanitization: No explicit sanitization or filtering of the retrieved data is mentioned or implemented in the scripts.
Audit Metadata