apimodels-image

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask the user to paste their API key into the conversation and to include that pasted key in a shell command (printf 'sk_THEIR_KEY' | ...), which requires the LLM to receive and place secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow (scripts/generate.mjs) ingests outsider-authored free text via the user-provided --prompt argument (and optional --image URLs) into the POST request body (prompt: args.prompt) sent to https://api.apimodels.app/v1/images/generations.