The Agent Skills Directory

[SAFE]: The skill documentation and implementation do not contain any malicious patterns, hardcoded credentials, or unauthorized network activity. All functionality aligns with the stated purpose of managing NFTs.
[PROMPT_INJECTION]: No instructions were detected that attempt to bypass AI safety filters or override system prompts. The agent instructions focus on safety checks such as ownership and balance verification.
[DATA_EXFILTRATION]: The skill only interacts with public Stacks blockchain APIs to fetch NFT data and broadcast signed transactions. No sensitive local data is accessed or transmitted.
[EXTERNAL_DOWNLOADS]: No remote scripts or unverified dependencies are downloaded or executed at runtime.
[COMMAND_EXECUTION]: Input handling is performed via the commander library, which provides structured CLI argument parsing. While the skill processes user-supplied contract IDs and token IDs, it performs basic validation such as integer parsing for token IDs.

nft