using-solution-architect

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes untrusted external design briefs, HLDs, and epics to generate architecture artifacts. While the workflow includes a 'Consistency Gate' to verify artifact quality, it lacks explicit data sanitization or boundary delimiters for processed content.
  • Ingestion points: User-supplied briefs and epic specifications processed in triaging-input-maturity.md.
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the input brief.
  • Capability inventory: The skill utilizes file system operations (ls, write) to manage architectural artifacts in the solution-architecture/ workspace.
  • Sanitization: No explicit sanitization or filtering of user-provided architectural descriptions is performed before interpolation into design documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:34 PM
Security Audit — agent-trust-hub — using-solution-architect