create-architectural-decision-record
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is limited to text generation and local file operations within the documentation directory. It does not perform network requests, access sensitive system files, or execute external code.
- [NO_CODE]: The skill consists exclusively of Markdown templates and instructions, with no executable scripts or third-party package dependencies.
- [PROMPT_INJECTION]: The skill ingests untrusted user data to generate documentation, presenting an indirect prompt injection surface. Ingestion points: Context, Decision, Alternatives, and Stakeholders inputs in SKILL.md. Boundary markers: Absent. Capability inventory: File writing to the /docs/adr/ directory. Sanitization: Absent. This surface is inherent to the functional purpose of the skill.
Audit Metadata