The Agent Skills Directory

[COMMAND_EXECUTION]: The wrapper script generate_infographic.py uses the subprocess.run function to invoke the main logic script generate_infographic_ai.py. The command is constructed using a list and sys.executable, which is a secure method that avoids shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill communicates with well-known AI service providers, specifically openrouter.ai and perplexity.ai, to generate images, review quality, and conduct web research. These network operations are intrinsic to the skill's stated functionality.
[SAFE]: Secret management follows industry standards by instructing users to provide API keys through environment variables or a local .env file, rather than hardcoding credentials.
[SAFE]: The skill implements a potential surface for indirect prompt injection when using the --research flag to ingest external web data. However, this is a primary feature for ensuring data accuracy, uses distinct text headers as boundary markers, and the risk is mitigated by the intended use case of generating static visual content.

infographics