Security audit
Security checks for vulnerabilities and agentic risk
The skill coherently documents MapleFlow’s paid API services, with expected external data processing and an optional local server that merits installation care.
Submit only content you authorize MapleFlow to process and expect requests to consume credits. MapleFlow’s [privacy policy](https://mapleflow.io/privacy/) says requests may be forwarded to AI providers. Prefer direct HTTP access, or review and pin the optional local MCP package before running it; keep your API key private.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
env:
- MAPLEFLOW_API_KEY
bins:
- curl
primaryEnv: MAPLEFLOW_API_KEY
---
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Use `GET /v1/models` for public chat model names. Read
`GET /openapi.json` for supported request fields and model enums, including
provider overrides. Both discovery endpoints are public. Interactive docs:
`https://api.mapleflow.io/docs`.
Use model names exactly as returned. Hosted model availability differs from
provider announcements; never invent a model ID or substitute a provider.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
max_tokens. Messages contain role and string content.
curl --fail-with-body https://api.mapleflow.io/ai/chat \
-H "X-API-Key: $MAPLEFLOW_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"messages":[{"role":"user","content":"Reply with OK"}],"model":"gpt-4o-mini","max_tokens":128}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
reserved before inference; unused credits are refunded after gateway cost
settlement. Minimum 0.01 credit; reduce `max_tokens` if the balance is insufficient.
OpenAI-compatible clients can use base URL `https://api.mapleflow.io/v1`,
API key `MAPLEFLOW_API_KEY`, and POST `/v1/chat/completions`. This endpoint
returns OpenAI-format JSON and accepts `max_tokens` or `max_completion_tokens`.
Streaming is not supported. The default chat model is `llama-3.2-1b` on
The executable example sends the contents of recording.wav to a third-party service, rather than merely listing an available endpoint. The skill does not warn that recordings, which may contain private conversations or sensitive information, leave the user's system.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
speech, and transcription responses use the formats documented in OpenAPI.
curl --fail-with-body https://api.mapleflow.io/ai/transcribe \
-H "X-API-Key: $MAPLEFLOW_API_KEY" -F 'audio=@recording.wav'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
## MCP access
Remote HTTP MCP: `https://api.mapleflow.io/mcp`. Use JSON-RPC `initialize`,
`tools/list`, and `tools/call`; tool calls require the API key header.
The npm stdio server is `npx -y @mapleflow/mcp-server`, configured with
`MAPLEFLOW_API_KEY`. It reads the live OpenAPI spec when it starts.
The unversioned npx -y @mapleflow/mcp-server command can download and execute a changing package release without an installation confirmation. A compromised future release could execute with the agent's local permissions and access the configured API key or other accessible data; the documentation does not establish that the package is currently malicious.
No suspicious patterns detected.