style-harmonizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes draft text from several input files which creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points:
sections/*.md,output/WRITER_SELFLOOP_TODO.md, andoutline/writer_context_packs.jsonl. - Boundary markers: Absent; there are no delimiters used to differentiate content from instructions.
- Capability inventory: The skill can read and write markdown files in the
sections/andoutput/directories. It has no capabilities for network operations, subprocess execution, or dynamic code evaluation. - Sanitization: Absent; input data is processed as raw text for the purpose of stylistic rewriting.
Audit Metadata