create-adr
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input describing architectural decisions and technical context to generate documentation.
- Ingestion points: User-provided descriptions of decisions, rationale, context, and forces are interpolated into documentation templates.
- Boundary markers: The skill uses structured questionnaires (Step 1) but does not define explicit delimiters or 'ignore' instructions for the final markdown output.
- Capability inventory: The skill lists the ADR directory (e.g.,
docs/adr/) to determine sequential numbering and writes new markdown files to the filesystem. - Sanitization: No explicit sanitization, validation, or escaping logic is defined for the user-supplied strings before they are written to the documentation files.
Audit Metadata