learn

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (date / Get-Date) to generate formatted timestamps for use in note metadata and filenames.
  • [COMMAND_EXECUTION]: The skill executes directory creation commands (mkdir -p / New-Item) to prepare the local filesystem for note storage at ~/Documents/notes.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where user-provided content is interpolated into file system paths.
  • Ingestion points: User input for the concept name ({概念名}) is directly used to generate a filename in SKILL.md.
  • Boundary markers: No delimiters or ignore-instructions are specified to protect the filesystem path from malicious user input.
  • Capability inventory: The skill possesses directory creation and file writing capabilities.
  • Sanitization: No sanitization or validation of the user-provided concept name is performed prior to its use in the file system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 03:16 PM