analyzing-options-flow

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to read exchange API credentials from a local .env via the Read tool and use them to authenticate against exchange endpoints, which requires the LLM to handle secret values and could lead to those secrets being embedded verbatim in requests/commands (exfiltration risk).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md and references/implementation.md explicitly require connecting to public exchange APIs/WebSocket feeds (Deribit, OKX, Bybit) and ingesting real-time options and block-trade data as part of its core workflow, so untrusted third-party market data is read and used to drive analysis and actions.