The Agent Skills Directory

[SAFE]: The skill is designed for local processing of scholarship applications. It uses a bundled Python script and standard libraries to generate reports without requiring network connectivity for its core functions.
[REMOTE_CODE_EXECUTION]: The skill utilizes a local Python layout engine (generate_report.py). Analysis of the script confirms it uses safe data handling practices, converting input to strings for PDF rendering and avoiding dynamic execution of user-supplied content.
[DATA_EXFILTRATION]: The skill collects Personally Identifiable Information (PII) necessary for the scholarship report. The analysis confirms this data remains within the local environment; the skill explicitly states it runs locally and contains no network-bound exfiltration logic.
[PROMPT_INJECTION]: The skill processes user-supplied academic profiles and web search results (Ingestion points). While it lacks explicit boundary markers for data separation, the agent's capabilities are confined to writing JSON files and running a static generation script. Sanitization is performed by the generation script which casts values to strings before rendering, minimizing the risk of indirect prompt injection affecting the host environment.
[EXTERNAL_DOWNLOADS]: Dependencies listed in requirements.txt are well-known, established libraries in the Python ecosystem (reportlab, matplotlib, numpy) and do not pose a supply-chain risk in this context.

scholarship-strategy-report