The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the litellm Python package, which is downloaded from the official Python Package Index (PyPI). This is an established library for managing multiple LLM providers.
[COMMAND_EXECUTION]: Executes local Python scripts scripts/perplexity_search.py and scripts/setup_env.py to perform searches and manage environment configuration. This is the intended primary functionality of the skill.
[CREDENTIALS_UNSAFE]: Manages an OPENROUTER_API_KEY through environment variables or a local .env file. The implementation provides utilities to securely store and retrieve this key for authentication, adhering to standard secret management practices.
[INDIRECT_PROMPT_INJECTION]: As a search tool, the skill ingests content from external web sources. This ingestion surface is mitigated by the skill's architecture, which returns search results as text without granting the processed data access to sensitive system commands or file operations.

alterlab-perplexity