req-outcome
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs (Lark documents) which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Untrusted content enters the agent's context through the
lark-cli docs +fetchcommand described in Step 1 and the terminal section. - Boundary markers: There are no explicit delimiters or warnings provided to the agent to disregard instructions embedded within the fetched document content.
- Capability inventory: The skill utilizes
meeglefor project searching, metadata retrieval, and adding comments to work items. - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from the external documents before it is used to form comments.
- [COMMAND_EXECUTION]: The skill's primary functionality is achieved through the execution of command-line interface (CLI) tools (
lark-cliandmeegle) with arguments derived from user input and external document content.
Audit Metadata