openhands-api-v1
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Communicates with official OpenHands Cloud API endpoints at
https://app.all-hands.devto retrieve conversation metadata, event logs, and trajectory data. These are trusted vendor resources for the OpenHands ecosystem.- [COMMAND_EXECUTION]: Provides programmatic wrappers for executing bash commands and managing files within an OpenHands sandbox environment via the/api/bash/execute_bash_commandand related agent-server endpoints. This is the intended core functionality of the skill.- [PROMPT_INJECTION]: The skill processes untrusted data in the form of conversation histories and external repository contents fetched via the API. This creates a surface for indirect prompt injection (Category 8); however, no malicious patterns were detected within the skill's own instructions, and it includes reminders for agents to maintain minimal calls and avoid long loops.
Audit Metadata