The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation defines several commands for executing a local script scripts/research.py to initiate research tasks, check status, and list results.- [EXTERNAL_DOWNLOADS]: The skill specifies the installation of Python dependencies from a requirements.txt file, including the httpx library, which is a common network request package.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its core functionality. Ingestion points: Data enters the system via the --query command-line argument and through external content retrieved from the web during the 'Deep Research' phase. Boundary markers: No specific delimiters or instructions to ignore embedded commands are documented for the query input or the synthesized research data. Capability inventory: The skill executes subprocesses (scripts/research.py) and performs network operations (API calls and web crawling). Sanitization: The documentation does not describe any validation or filtering of user-supplied queries or external information retrieved during the research process.

deep-research