mixture-of-experts

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill is designed to ingest and analyze arbitrary external content.
  • Ingestion points: According to the 'Workflow' section in SKILL.md, the skill processes any user-provided topic, architecture plan, codebase, or process.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the target content.
  • Capability inventory: The skill utilizes invoke_subagent to spawn specialized experts and performs file-system writes to create artifacts such as consolidation_learnings.md.
  • Sanitization: No validation or sanitization mechanisms are described for handling the untrusted data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:41 PM
Security Audit — agent-trust-hub — mixture-of-experts