de-ai-ify
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions for text transformation. It does not include any executable code, shell scripts, network requests, or attempts to access sensitive system files.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text files, which constitutes an indirect prompt injection surface.\n
- Ingestion points: User-provided text files processed according to the 'Process' section in SKILL.md.\n
- Boundary markers: No specific delimiters or safety instructions are defined to separate user content from agent instructions.\n
- Capability inventory: The skill involves reading existing files and writing new files with a '-HUMAN' suffix as described in SKILL.md.\n
- Sanitization: No explicit sanitization or filtering of input text is mentioned. \nSince the skill only performs stylistic text rewriting and does not execute the content of the files, this surface represents a low-risk, standard operational context for text-editing tasks.
Audit Metadata