Skills
Navigate
skills/jeffallan/claude-skills/architecture-designer/Gen Agent Trust Hub

architecture-designer

Fail

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL that has been flagged as malicious by automated security scanners.
  • Evidence: https://jeffallan.github.io/claude-skills/skills/api-architecture/architecture-designer/ in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted functional and non-functional requirements to generate architectural designs without proper sanitization or boundary markers.
  • Ingestion points: SKILL.md (Workflow Step 1)
  • Boundary markers: Absent
  • Capability inventory: Generates system architecture diagrams and decision records
  • Sanitization: Absent
Recommendations
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Oct 4, 2026, 04:47 AM