fastapi-pro
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied technical requirements and code snippets to generate FastAPI implementations, creating an attack surface for indirect instructions.
- Ingestion points: User-provided goals, constraints, and code examples mentioned in the 'Instructions' and 'Example Interactions' sections of
SKILL.md. - Boundary markers: The instructions do not define delimiters (like triple backticks or XML tags) or specific warnings to ignore instructions embedded within the user-provided data.
- Capability inventory: The skill has extensive capabilities including file implementation, network operations via
httpx, and database interactions (SQLAlchemy, Redis, MongoDB), which could be triggered by injected instructions. - Sanitization: There are no instructions for the agent to sanitize or validate the content of user-provided data before processing it as a requirement.
Audit Metadata