openclaw-add-feishu-bot
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several shell commands to facilitate the setup process:
- Creates a workspace directory using
mkdir -p. - Restarts the openclaw gateway service using
launchctl kickstart. - Executes the
openclaw pairing approvecommand to finalize bot registration. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses and modifies the local configuration file at
~/.openclaw/openclaw.json. This file contains application identifiers and secrets (appId,appSecret). The handling of these credentials is part of the legitimate configuration workflow and no external data exfiltration was detected. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it reads the existing
openclaw.jsonfile. It mitigates risk by performing structured edits (JSON manipulation) rather than arbitrary execution of file contents. The potential impact is limited to the local configuration of the openclaw service.
Audit Metadata