li-analyzer

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. All operations are consistent with the skill's stated purpose of content analysis.
  • [DATA_EXPOSURE]: The skill reads from local directories (03-数据统计/, 02-已发布内容/) to perform analysis. This access is limited to the user's content data and is necessary for the skill's core functionality.
  • [COMMAND_EXECUTION]: The skill does not execute any shell commands, subprocesses, or dynamic code.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided video scripts and data tables. While this creates a surface for indirect prompt injection, the skill's capabilities are limited to reading these files and writing a report, presenting low risk. No specific sanitization or boundary markers were identified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 02:18 PM