infographics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes a --api-key CLI option and examples that show passing API keys on the command line (and a placeholder export), which encourages embedding secret values verbatim into commands or generated code and therefore creates an exfiltration risk despite also mentioning the safer env-var approach.

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

• Third-party content exposure detected (high risk: 0.85). The skill’s --research path calls Perplexity Sonar Pro (research_topic() → requests.post to perplexity/sonar-pro), and the returned web-sourced free text (research_data['content']) is then injected into the LLM prompt for infographic generation via _enhance_prompt_with_research() → _build_generation_prompt().

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime requests to the OpenRouter API (https://openrouter.ai/api/v1) to (optionally) fetch Perplexity Sonar research content and to obtain Gemini/Nano Banana model responses whose content (research output and review critiques) is injected into and directly controls subsequent prompts and regeneration logic, and the skill requires an OpenRouter API key to operate.