lark-workflow-content-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executed via
lark-cli, a dedicated command-line boundary utility configured globally under platform constraints. All invocations represent normal platform management flows such as database creation and record synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill processes user conversations and third-party group chat messages (
lark-cli im +chat-messages-list), creating a potential ingestion surface for instruction interpolation. However, it handles inputs primarily as standard payload elements to evaluate and persist in structured records rather than running arbitrary dynamic content.
Audit Metadata