The Agent Skills Directory

[SAFE]: The skill consists of technical documentation and code examples for report generation. All demonstrated behaviors involve local file processing and standard API data retrieval for the purpose of creating documents.
[COMMAND_EXECUTION]: The provided code snippets utilize standard data processing and visualization libraries (pandas, matplotlib, reportlab). All file system interactions (saving PDFs and charts) are conducted through well-documented, legitimate APIs.
[EXTERNAL_DOWNLOADS]: The skill references standard Python packages (e.g., jinja2, weasyprint, plotly) which are well-known tools for document generation and data analysis.
[PROMPT_INJECTION]: The skill defines a system for processing external data into PDF reports. While it does not contain malicious instructions, the documented use of autoescape=False in Jinja2 templates represents an attack surface for indirect prompt injection if untrusted data is processed without prior sanitization.
Ingestion points: pd.read_csv, json.load, and requests.get() calls in SKILL.md.
Boundary markers: None present in the example code.
Capability inventory: File system writes via weasyprint.HTML().write_pdf() and plt.savefig().
Sanitization: Not explicitly implemented in the provided code snippets.

report-generation