The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the litellm package from PyPI for API interaction. It also suggests using python-dotenv for environment management and jq for processing results, which are standard developer tools.- [COMMAND_EXECUTION]: The skill includes two Python scripts: scripts/perplexity_search.py for search execution and scripts/setup_env.py for configuration. These scripts use standard libraries like argparse, os, and json, and do not perform any unsafe operations such as arbitrary code execution or shell injection.- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes data from external web sources. \n
Ingestion points: Search results are fetched from Perplexity AI via OpenRouter in scripts/perplexity_search.py and returned to the agent context. \n
Boundary markers: The skill does not use specific delimiters or protective instructions to distinguish search results from system instructions. \n
Capability inventory: The skill has the capability to write output to a user-specified file path (scripts/perplexity_search.py) but does not include any dynamic execution functions like eval() or exec(). \n
Sanitization: No filtering or sanitization is applied to the retrieved web content before it is processed by the agent.

perplexity-search