The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted user data to populate code templates for chart generation, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: User input provided via the [数据描述/图表需求] argument in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user data.
Capability inventory: The skill utilizes Bash, Write, and Edit tools to generate and execute local scripts (SKILL.md).
Sanitization: No input validation or escaping mechanisms are implemented in the provided Python or JSA templates.
[COMMAND_EXECUTION]: The workflow relies on dynamic execution patterns where the agent writes code to the file system (e.g., chart_output.xlsx) and is encouraged to run it using local interpreters like Python or WPS Macro environments.

wps-chart