doctoreto
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and encourages the use of an external Python package
doctoreto-mcpvia theuvxtool. This package is required to provide the backend tool logic for interacting with Doctoreto's APIs. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it retrieves and processes untrusted, third-party content from the Doctoreto website.
- Ingestion points: Untrusted data enters the context through patient reviews (
dt_reviews), health magazine articles (dt_health_articles), and doctor/center descriptions. - Boundary markers: There are no explicit instructions or delimiters used to separate user-provided or web-retrieved content from the agent's core instructions.
- Capability inventory: The tools are restricted to read-only operations (searching and viewing data) and do not include capabilities for file system modification, network exfiltration, or shell execution.
- Sanitization: The instructions do not specify any mechanisms for sanitizing or filtering the content fetched from the external APIs before it is interpreted by the agent.
Audit Metadata