architecture-principles
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes various technical and business inputs to generate its deliverables, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill gathers business outcomes, failure impacts, quality priorities, and hard constraints in the 'Inputs To Gather' section of SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded in the input data.
- Capability inventory: The skill includes a local script (
scripts/validate_architecture_contract.py) but does not have access to high-risk tools such as network operations, privileged system writes, or arbitrary command execution. - Sanitization: The skill lacks explicit sanitization or validation routines for the descriptive data it ingests before generating the principle catalog and review checklists.
Audit Metadata