The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data, including token symbols, amounts, and trigger prices, and interpolates them into bash commands for the nansen CLI. This creates a surface where specially crafted input could influence the constructed command flags.
Ingestion points: Command flags in SKILL.md such as --from, --to, --amount, and --trigger-price are populated with user input.
Boundary markers: None identified in the instruction templates to delimit user input from the command structure.
Capability inventory: The skill is authorized to execute Bash(nansen:*) as specified in the allowed-tools metadata.
Sanitization: No explicit sanitization or validation of user input is defined within the skill instructions, relying on the underlying CLI tool for processing.
[EXTERNAL_DOWNLOADS]: The skill downloads and installs the official nansen-cli package from the public npm registry during setup.
Evidence: The install section in SKILL.md specifies package: nansen-cli using the node installer.

nansen-limit-orders