didit-email-verification
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided email addresses and OTP codes to facilitate verification, which creates a standard attack surface for indirect instructions within that data. \n- Ingestion points: User inputs received as command-line arguments in scripts/verify_email.py. \n- Boundary markers: The skill does not employ explicit boundary markers or instructions to isolate the user-supplied strings. \n- Capability inventory: The skill is capable of performing network POST requests using the requests library to external didit.me endpoints. \n- Sanitization: The implementation uses standard JSON encoding when building the API request body, providing protection against malformed JSON structure but not against content-based injection.
Audit Metadata