architecture-designer

Fail

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided technical requirements to generate architectural designs, which presents a standard attack surface for indirect prompt injection.
  • Ingestion points: User-supplied functional and non-functional requirements gathered in step 1 of the Core Workflow in SKILL.md.
  • Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore embedded commands in the input data.
  • Capability inventory: None. The skill's scope is restricted to generating text-based documents (ADRs) and diagrams (Mermaid). It lacks tools for file writing, network exfiltration, or shell execution.
  • Sanitization: Absent. Input requirements are processed directly into the design workflow without validation.
  • [EXTERNAL_DOWNLOADS]: SKILL.md contains a link to documentation at jeffallan.github.io. While this domain has been flagged by external reputation services, it is a vendor-owned resource hosted on a well-known service (GitHub Pages) used for project documentation. No automated downloads or execution of remote code are performed.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 15, 2026, 11:24 AM
Security Audit — agent-trust-hub — architecture-designer