de-ai-ify

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional markdown and configuration metadata. No executable code or binary files are included. Logic is implemented via the agent's interpretation of provided patterns.
  • [SAFE]: No evidence of malicious behavior such as data exfiltration or obfuscation was identified. The skill claims to operate offline and does not include any network-related commands.
  • [PROMPT_INJECTION]: As the skill is designed to process and transform external text files, it has a surface for indirect prompt injection.
  • Ingestion points: Reads user-provided .md, .txt, and .docx files (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
  • Capability inventory: Reads input files and writes output to a new file with a -HUMAN.md suffix.
  • Sanitization: No sanitization of input text is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:12 AM