The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands via the Bash tool to inspect the project environment (e.g., cat package.json, rg) and to verify the generated code using build tools (npx tsc, npm run build).
[EXTERNAL_DOWNLOADS]: The skill initiates the installation of the openalgo-charts package using npm install. This is the intended behavior of the skill and aligns with the author's ecosystem.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing project metadata to drive execution.
Ingestion points: The skill reads and searches the project's package.json file using cat and rg to detect the framework.
Boundary markers: There are no boundary markers or explicit instructions to ignore embedded commands within the ingested package.json data.
Capability inventory: The skill has access to the Bash tool and performs write operations. It uses these capabilities to execute project-defined scripts during the verification phase (npm run build).
Sanitization: No sanitization or validation is performed on the content of the package.json file before its defined scripts are executed by the agent.

openalgo-chart-setup