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