logo-batch-generator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes example commands and a config table that pass an API key as a command-line argument (--api-key "REMOVED_GEMINI_KEY") and lists the API Key value, which would require the LLM to include secret values verbatim if real keys are used.

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

• Third-party content exposure detected (medium risk: 0.30). Skill runtime takes outsider-supplied brand name/description (模式A) and uploaded image analysis results/derived elements (模式B) to construct Gemini image-generation prompts, meaning arbitrary user-provided free text is ingested into the LLM without selecting a specific item first.