The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process raw data from users or external research sources to generate complex HTML and SVG visualizations.
Ingestion points: Raw data or research findings are requested from the user in SKILL.md Step 1.
Boundary markers: While the skill provides a strict design system and output template in SKILL.md Steps 3 through 8, it does not explicitly instruct the agent to ignore or sanitize embedded instructions within the ingested data.
Capability inventory: The agent is authorized to write files to the local filesystem and is specifically instructed to execute the open command in SKILL.md Step 9.
Sanitization: There are no documented sanitization or validation routines for external data processed by the skill.
[COMMAND_EXECUTION]: SKILL.md explicitly instructs the agent to execute a shell command to perform visual quality assurance.
Evidence: Step 9 of SKILL.md directs the agent to "Save the chart as an HTML file" and "Open it in the browser (use open command)". This pattern involves executing a local command on a file path generated by the agent, which may contain user-controlled data.

create-geo-charts