base44-platform-integrations-sdk
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exposes the agent to untrusted external data, creating a potential surface for indirect prompt injection.
- Ingestion points: Untrusted data enters via
InvokeLLM(throughfile_urlsandadd_context_from_internet),TranscribeAudio(audio_url), andExtractDataFromUploadedFile(file_url) as described inreferences/mobile.md,references/web-spa.md, andreferences/web-tanstack.md. - Boundary markers: The documentation does not prescribe the use of specific delimiters to isolate external content within the agent's prompt context.
- Capability inventory: The skill possesses powerful capabilities such as sending emails (
SendEmail) and push notifications (SendPushNotification), which could be misused if the agent is compromised by malicious data. - Sanitization: The SDK documentation explicitly warns against routing untrusted input to email recipients and mentions that the backend performs content screening for abuse prevention.
Audit Metadata