The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_infographic.py uses subprocess.run() to execute the internal AI generation script. The call uses a list-based argument structure and avoids a shell environment, which is a safe implementation for chaining internal scripts.- [EXTERNAL_DOWNLOADS]: The skill makes network requests to the OpenRouter API (openrouter.ai) in scripts/generate_infographic_ai.py. This is a well-known service used to access the models required for the skill's primary function of infographic generation and research.- [PROMPT_INJECTION]: The skill features an automated research integration that presents a surface for indirect prompt injection. 1. Ingestion points: The research_topic and web_search methods in scripts/generate_infographic_ai.py fetch untrusted content from the internet via the Perplexity Sonar model. 2. Boundary markers: The researched data is interpolated into the generation prompt under a RESEARCHED DATA AND FACTS header, but it lacks robust delimiters or explicit instructions to ignore embedded malicious commands. 3. Capability inventory: The skill is capable of writing image and log files to the local file system and making further API requests to OpenRouter. 4. Sanitization: The skill does not sanitize or filter the content returned from web research before including it in the prompts for the image generation model.

infographics