skills/lijigang/ljg-skills/ljg-rank/Gen Agent Trust Hub

ljg-rank

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command date to generate formatted timestamps for use in filenames and document metadata.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by interpolating user-provided input ('领域' or domain) into a local file system path and shell-derived filename without providing sanitization or validation logic.
  • Ingestion points: User input provided for the '领域' variable in the prompt.
  • Boundary markers: Absent; user-provided data is used directly to construct the file path and name.
  • Capability inventory: Local file system write access (~/Documents/notes/) and shell command execution (date).
  • Sanitization: Absent; there are no instructions to escape characters or validate the input before it is used in the file path construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 04:52 AM