openclaw-lark-integration
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@larksuite/openclaw-larkandopenclawpackages from the official npm registry. These are expected dependencies for the described functionality. - [COMMAND_EXECUTION]: The documentation includes standard CLI commands for starting and operating the OpenClaw service.
- [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by handling untrusted data from external sources.
- Ingestion points: Reads content from Lark messages, documents, and Base records (SKILL.md).
- Boundary markers: Absent. No delimiters or warnings are provided to help the agent distinguish between instructions and data.
- Capability inventory: The skill is capable of performing write operations such as sending messages, creating documents, and managing database records (SKILL.md).
- Sanitization: Absent. The skill relies on the AI's internal guardrails and user-configured policies.
- [SAFE]: No malicious intent, obfuscation, or data exfiltration patterns were identified. The skill correctly implements security policies like group whitelisting and uses environment variables for credential management.
Audit Metadata