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, and outline/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/ and output/ 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
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:04 PM