de-ai-ify

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (raw text or file content) provided via arguments. This creates a surface for indirect prompt injection where malicious instructions embedded in the source text could influence the agent's behavior.
  • Ingestion points: Processes data from the $ARGUMENTS variable, which can contain raw text or a file path to be read (Step 1).
  • Boundary markers: The skill does not implement delimiters or explicit 'ignore instructions' warnings for the processed text.
  • Capability inventory: The skill has permissions to read local files and write new files to the filesystem with a -HUMAN suffix (Step 5).
  • Sanitization: No input validation or sanitization is performed on the text content prior to processing.
  • [COMMAND_EXECUTION]: The skill performs filesystem operations, including reading files and writing copies of files based on user-supplied paths. This is consistent with the primary purpose of the skill but involves interacting with the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:09 PM