matplotlib
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
emacsclientwith the--evalflag to retrieve system UI information (foreground color). - [DYNAMIC_EXECUTION]: The skill follows a pattern of writing a Python script to a temporary file (
/tmp/agent-plot-XXXX.py) and executing it at runtime viauv run --with matplotlib. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an attack surface because it derives 'plottable data' from the conversation context and interpolates it into a Python script template. If this data is maliciously crafted, it could lead to arbitrary code execution within the Python environment.
Audit Metadata