architecture-design

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, potentially untrusted data such as user-supplied requirements, design briefs, and repository source code.
  • Ingestion points: The skill reads requirements paths, repository documents (ADRs, manifests), and samples existing code and tests as defined in the Inputs and Procedure sections of SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined in SKILL.md to isolate external input or direct the agent to ignore instructions embedded within that data.
  • Capability inventory: The skill utilizes file read operations and file write operations to specific template paths (../../resources/templates/design.md) as defined in SKILL.md. It does not demonstrate network access or arbitrary command execution capabilities.
  • Sanitization: SKILL.md lacks explicit validation or sanitization routines for the content of the files it ingests.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 04:00 AM
Security Audit — agent-trust-hub — architecture-design