The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied wallet addresses which are interpolated directly into shell commands. This creates a surface where malformed input could potentially attempt command injection if the underlying agent platform does not provide sufficient sanitization.
Ingestion points: The $ADDR variable in the Bash examples within SKILL.md captures external wallet addresses.
Boundary markers: The skill does not define specific delimiters or instructions to treat the address strictly as data.
Capability inventory: The skill utilizes the Bash(nansen:*) tool for execution.
Sanitization: No explicit sanitization or validation logic is defined within the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of nansen-cli via Node.js. This is the official command-line interface for the Nansen platform and is a necessary dependency for the skill's primary functionality.
[COMMAND_EXECUTION]: The skill instructions provide specific Bash command patterns using the nansen binary, such as nansen research portfolio defi and nansen research profiler balance, to fetch and combine on-chain exposure data.

nansen-defi-positions