The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and structural templates. No scripts, binaries, or automated tool configurations are included.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an injection surface as it ingests untrusted user input to generate chart recommendations.
Ingestion points: The Required Inputs section in SKILL.md describes taking user-provided sentences and data shapes.
Boundary markers: Absent; the skill does not explicitly instruct the agent to distinguish between instructions and data.
Capability inventory: None. The skill does not define or use any tools that allow for command execution, file system modification, or network communication.
Sanitization: Absent; input is used directly for text generation.
Evaluation: While the skill processes untrusted input, the complete lack of dangerous capabilities means this surface cannot be exploited to perform malicious actions beyond text generation.

chart-choice