limitless
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill communicates exclusively with the official Limitless AI domain (api.limitless.ai) to retrieve and manage lifelog data.
- [EXTERNAL_DOWNLOADS]: Downloads audio files (Ogg Opus format) from the official Limitless API to the local system upon user request. This follows the trust rule for well-known services.
- [PROMPT_INJECTION]: The skill processes conversation transcripts and chat history which represent untrusted data that could contain instructions intended to influence the agent's behavior. Ingestion points: Transcripts and summaries are fetched via the /lifelogs and /chats endpoints in the limitless script. Boundary markers: No explicit delimiters or warnings are used when presenting transcripts to the agent. Capability inventory: The skill possesses network access (via httpx), file writing capabilities (for audio), and the ability to delete remote resources. Sanitization: Data retrieved from the API is formatted into Markdown without filtering for potential injection patterns.
Audit Metadata