The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from the TON documentation site and GitHub to generate responses.
Ingestion points: Data is retrieved from the TON Docs MCP server via the search_ton_docs and get_page_ton_docs tools defined in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the retrieved external content.
Capability inventory: The agent uses the fetched documentation content to synthesize answers and generate smart contract code examples.
Sanitization: There is no evidence of filtering or sanitization of the remote content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references and fetches information from official TON blockchain resources.
Resources: Fetches content from the TON Docs MCP server at https://docs.ton.org/mcp and refers to standards in the ton-blockchain GitHub organization.
Vendor Context: These resources are the official documentation and standards repositories for the TON ecosystem.

ton-docs