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

ljg-rank

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the standard system utility date twice to generate formatted timestamps for use in filenames and document metadata.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it interpolates user-provided domain names directly into a file path template without explicit sanitization instructions.
  • Ingestion points: User input for the target 'domain' (領域) used in the filename and document header.
  • Boundary markers: None present to delimit user input from the shell-adjacent file path construction.
  • Capability inventory: System command execution (date) and file system write access to ~/Documents/notes/.
  • Sanitization: Not explicitly mentioned; the skill relies on the agent's internal safety controls for handling special characters in filenames.
  • [SAFE]: No evidence of malicious behavior was found. The skill does not perform network operations, use obfuscated code, access sensitive credentials, or attempt to maintain persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 04:22 PM