gi-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the agent to prompt the user for an API Key and shows/accepts commands that include --apikey/--api-key overrides (and saves the key to a config file), which requires handling and potentially outputting secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls an arbitrary external API (apiBaseUrl) and parses streaming JSON/events and returned image URLs from that endpoint—see scripts/generate-image.mjs (callImageEndpoint, readStreamResponse, pickImage, saveGeneratedImage) and the SKILL.md /gi workflow—so untrusted third‑party responses are ingested and can directly influence fallback/retry logic and generation outcomes.