flask
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides examples of handling external data via web requests (e.g., using
request.get_json()and route parameters). While this is the intended function of the web framework, it establishes a data ingestion surface that could be used for indirect prompt injection if user-supplied data is subsequently processed by an AI agent without sanitization. - Ingestion points: SKILL.md (e.g.,
request.get_json(), route parameters inuser_bp.route) - Boundary markers: Absent
- Capability inventory: The skill documents capabilities for network operations and database management through Flask extensions.
- Sanitization: Examples include basic type validation (e.g.,
<int:user_id>) and presence checks, which are standard for the documented use case.
Audit Metadata