skills/yelban/ljg-skills.tw/ljg-think/Gen Agent Trust Hub

ljg-think

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the date command to obtain formatted timestamps for naming and organizing output files.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8). Ingestion point: user-provided viewpoints processed by the agent. Boundary markers: none specified in SKILL.md. Capability inventory: execution of the date command and file writing to the ~/Documents/notes/ directory as defined in the skill logic. Sanitization: absent. While the skill lacks explicit delimiters or sanitization for user input used in filenames or content, the security impact is minimized by its local operation and the absence of network capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 01:50 AM