lx-connector

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'lx' command-line interface to interact with Tencent Lexiang services. Commands such as 'lx meeting search-tx-meeting-records' and 'lx comment list-comments' are used to retrieve and manipulate data.
  • [PROMPT_INJECTION]: Surface for Indirect Prompt Injection detected.
  • Ingestion points: Data is ingested from external Tencent Meeting records (transcripts/metadata) and comments on knowledge base entries via the 'lx meeting' and 'lx comment' tools.
  • Boundary markers: Absent. The skill instructions do not define specific delimiters or provide guidance to the agent to ignore instructions embedded within the meeting content or comments.
  • Capability inventory: The skill includes the ability to write to the knowledge base using 'lx meeting import-tx-meeting-record'.
  • Sanitization: Absent. There is no logic provided in the skill to sanitize or validate the content of meeting records or comments before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 09:42 PM
Security Audit — agent-trust-hub — lx-connector