lark-workflow-stock-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
lark-clibinary to interact with the Lark platform's Base, Docs, and IM services. This includes creating tables, reading/writing records, and sending messages. These actions are performed under the user's authentication context (lark-cli auth login). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved via
WebSearchto perform earnings analysis, stock picking, and research. This introduces a surface where malicious instructions embedded in web content could potentially influence the agent's summarization or reporting. - Ingestion points: External data from financial websites and stock market search results (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the analysis workflow.
- Capability inventory: The agent can write to Lark Base tables (
+record-upsert), create documents (docs +create), and send IM messages (im +messages-send). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the web before it is processed by the AI analyst roles.
Audit Metadata