trading-psychology

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted user data (trade journals and source code) to provide psychological feedback.
  • Ingestion points: User-provided trade journals and local source code files (referenced in SKILL.md and references/validations.md).
  • Boundary markers: Absent. The instructions do not define delimiters or system instructions to ignore embedded commands in the user-provided data.
  • Capability inventory: Analysis and review limited to natural language advice. No file-write, network-send, or code-execution capabilities were detected.
  • Sanitization: Absent. External content is processed directly to identify patterns.
  • Metadata (LOW): The skill references internal files (references/patterns.md and references/sharp_edges.md) that are missing from the package, which prevents a comprehensive audit of all grounding instructions.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:03 AM