architecture-decision-framework
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework directs the agent to analyze external artifacts such as source code, configuration files, and documentation to verify architectural premises.
- Ingestion points: Technical artifacts including source code and configuration files (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within external data are provided.
- Capability inventory: The skill involves generating text recommendations and writing Architecture Decision Records (ADRs) to the filesystem.
- Sanitization: No explicit sanitization of external content is specified.
- [DYNAMIC_EXECUTION]: The framework recommends using simple scripts to verify the arithmetic in decision scoring matrices.
- Evidence: The instruction in references/scoring.md to 'Check arithmetic with a calculator or short script.'
- Context: This is a low-risk recommendation for local calculation verification.
Audit Metadata