fcm-push-notifications
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of device tokens from external sources, creating a surface for indirect prompt injection if those tokens are maliciously crafted.
- Ingestion points:
references/token-management.mddefines aregisterTokenmethod that accepts a token string originating from the user's device. - Boundary markers: The snippets do not include explicit validation or delimitation for the token string before it is stored in the database or used in messaging operations.
- Capability inventory: The skill code involves database write operations via Prisma (
references/token-management.md) and external network communication via thefirebase-adminSDK (references/backend-fcm.md). - Sanitization: No evidence of token input sanitization or validation is present in the provided implementation examples.
Audit Metadata