The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the neural-trader package from the NPM registry using npm install. It follows security best practices by including the --ignore-scripts flag, which prevents the execution of arbitrary lifecycle scripts during the installation process.
[COMMAND_EXECUTION]: The skill uses npx to execute commands from the neural-trader package to perform risk assessments, calculate Value at Risk (VaR), and check circuit breaker statuses.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data which could lead to instruction injection if the inputs are not properly sanitized.
Ingestion points: The skill accepts external input through the --symbol (TICKER) and --portfolio (NAME) arguments in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat these interpolated variables as untrusted data.
Capability inventory: The skill possesses the capability to execute shell commands via the Bash tool to run npm and npx operations.
Sanitization: The instructions do not define any validation, escaping, or filtering logic for the ticker symbols or portfolio names before they are passed to the shell environment.

trader-risk