de-ai-ify

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Exposure to indirect prompt injection through data ingestion.
  • Ingestion points: The skill reads external data from a user-specified <file_path> in the SKILL.md process description.
  • Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the processed file.
  • Capability inventory: The skill has the capability to read files and write new files (creating copies with a '-HUMAN' suffix).
  • Sanitization: No evidence of sanitization or validation for the content of the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 10:39 PM