iblai-api-agent-memory
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages memories extracted from user interactions that are later interpolated into system prompts. * Ingestion points: User-provided conversation text processed by backend services. * Boundary markers: Injected memories use Markdown headers as delimiters. * Capability inventory: API-driven memory management (CRUD). * Sanitization: Backend LLM-based extraction and deduplication logic.
- [SAFE]: All external communications target the vendor's official domain (api.iblai.app).
- [SAFE]: Secret management follows best practices by using environment variables rather than hardcoded credentials.
Audit Metadata