markdown-writer

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external markdown files which may contain malicious instructions.
  • Ingestion points: Markdown files are read from the filesystem using the Read tool.
  • Boundary markers: Absent; the skill does not use delimiters to isolate file content.
  • Capability inventory: The skill employs Read, Write, Edit, and Grep tools to modify the local filesystem.
  • Sanitization: Absent; the skill does not validate or filter the content of processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 06:23 AM