Skills
skills/lijigang/ljg-skills/ljg-constraint/Gen Agent Trust Hub

ljg-constraint

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command date twice using different formats (+%Y%m%dT%H%M%S and "+%Y-%m-%d %a %H:%M"). This is used solely to generate unique timestamps for file naming and report metadata.
  • [FILE_SYSTEM_ACCESS]: The skill performs local file writes to ~/Documents/notes/. The generated filenames incorporate the domain name provided by the user and the generated timestamp. This is the primary output method for the skill's analytical work.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 11:48 AM
Security Audit — agent-trust-hub — ljg-constraint