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 +fetch command 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 meegle for 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-cli and meegle) with arguments derived from user input and external document content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 02:15 AM