The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the TON blockchain via the get_nfts and get_nft tools, which retrieve NFT names, descriptions, and other metadata provided by third parties.
Ingestion points: NFT metadata and collection details fetched through blockchain query tools in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions embedded within the metadata.
Capability inventory: The skill provides the send_nft tool, enabling the agent to initiate asset transfers on behalf of the user.
Sanitization: No sanitization or validation of external content is mentioned before it enters the agent's context.

ton-nfts