create-architectural-decision-record
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates locally to create documentation files based on user input. It does not perform network operations, execute arbitrary code, or access sensitive system credentials.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it interpolates user-provided text into a Markdown document. Ingestion points: Context, Decision, Alternatives, and Stakeholders input variables. Boundary markers: None. Capability inventory: Writing files to the /docs/adr/ directory. Sanitization: None specified. This behavior is inherent to the skill's purpose and poses minimal risk.
Audit Metadata