lx-comment

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'lx' CLI for its primary functions, specifically the 'lx comment list-comments' and 'lx comment describe-comment' commands to interact with comment data.
  • [EXTERNAL_DOWNLOADS]: The skill requires the 'lx' binary to be present on the system. This binary is a tool associated with the skill's author, 'tencent-lexiang'.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it fetches and processes external data (comments) that may contain instructions designed to influence the agent's behavior.
  • Ingestion points: Data returned from 'lx comment list-comments' and 'lx comment describe-comment' contains user-generated comment text.
  • Boundary markers: No specific delimiters or instruction-ignore blocks are defined for the comment content.
  • Capability inventory: The toolset provided in this skill is restricted to read operations (listing and describing comments), which limits the impact of potential injections.
  • Sanitization: The skill notes that comment content requires special parsing but does not provide specific sanitization or filtering instructions to mitigate malicious content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 09:42 PM
Security Audit — agent-trust-hub — lx-comment