imperial

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is configured to ingest and process data from external, untrusted sources, which creates a potential indirect prompt injection vulnerability surface.
  • Ingestion points: Market/portfolio intelligence data and Telegram bot trading workflows (SKILL.md).
  • Boundary markers: Absent; the instructions do not define delimiters or system prompts to isolate untrusted input from agent instructions.
  • Capability inventory: The skill coordinates order execution via the POST /api/v1/mobile/orders endpoint and handles trading strategy workflows such as TWAP and grid bots.
  • Sanitization: Absent; no specific validation, filtering, or escaping mechanisms for external inputs are described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:45 PM
Security Audit — agent-trust-hub — imperial