how

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of untrusted external content (the user's codebase and configured artifacts) through the /domain-modeling and /swarm tools. This creates an attack surface where malicious instructions embedded in the analyzed code could potentially influence the agent's output or explanation logic.
  • Ingestion points: The skill reads the invoking project's configured artifacts and explores the codebase to answer architectural questions.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided prompts.
  • Capability inventory: The skill utilizes /swarm for read-only subagent delegation and /domain-modeling for artifact resolution. It performs read-only investigations of the filesystem.
  • Sanitization: No evidence of sanitization or filtering of codebase content before processing was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 07:57 AM