line-chart-generator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from files and command-line arguments, creating an attack surface where malicious instructions could be embedded in the processed data.
- Ingestion points: The
--data-fileargument inscripts/generate_chart.pyreads and parses JSON files provided at runtime. - Boundary markers: No specific boundary markers or instructions are defined to separate chart data from agent instructions.
- Capability inventory: The skill contains file read (
json.load) and file write (plt.savefig) capabilities across its scripts. - Sanitization: The script enforces JSON structure and type-casting (dates and floats), which provides basic validation but does not filter for natural language instructions.
- [COMMAND_EXECUTION]: The skill involves the execution of a local Python script (
scripts/generate_chart.py) to perform chart generation. - [EXTERNAL_DOWNLOADS]: The skill requires the
matplotliblibrary, which is a well-known and trusted third-party package for Python.
Audit Metadata