The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script scripts/research.py to manage the research workflow, search logic, and interaction with the Gemini API.
[EXTERNAL_DOWNLOADS]: The skill requires installing Python dependencies via pip install -r requirements.txt from a source repository (sanjay3290/ai-skills) that does not belong to a trusted organization or well-known vendor.
[PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating an indirect prompt injection surface.
Ingestion points: External websites, search results, and technical documents read during the research process.
Boundary markers: No delimiters or explicit instructions to ignore embedded commands within retrieved data are documented.
Capability inventory: The skill possesses network access via httpx and the ability to execute local scripts.
Sanitization: There is no evidence of sanitization or validation of external content before it is interpolated into prompts for synthesis.

deep-research