bmad-os-diataxis-style-fix
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes external markdown files which could contain malicious instructions.
- Ingestion points: Documentation files or directories (defaulting to
docs/) and the project style guidedocs/_STYLE_GUIDE.md. - Boundary markers: Absent; the skill reads and processes the content of these files directly without delimiters or explicit 'ignore' instructions.
- Capability inventory: The skill uses an 'Edit tool' to modify local files.
- Sanitization: Absent; the skill performs regex-like pattern matching and replacements without sanitizing the input data.
- Mitigation: The
disable-model-invocation: trueflag in the YAML frontmatter significantly reduces the risk of the agent's core reasoning being hijacked, as it likely uses a deterministic path for text transformation.
Audit Metadata