The Agent Skills Directory

[SAFE]: The skill provides legitimate blockchain management functionality consistent with its description. It correctly directs users to secure methods for handling sensitive data, such as using environment variables for API keys and passwords.
[EXTERNAL_DOWNLOADS]: The skill references setup and troubleshooting documentation on the vendor's official GitHub repository (github.com/PrintrFi/printr-mcp). This is a well-known and appropriate source for technical documentation.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves and processes external blockchain data, such as token metadata and deployment statuses. However, this is an inherent aspect of blockchain interaction and the risk is considered low in this context.
Ingestion points: Token metadata, deployment statuses, and staking positions are ingested through tools like printr_get_token, printr_get_deployments, and printr_get_staking_positions.
Boundary markers: None identified in the provided instructions.
Capability inventory: The skill has the capability to perform financial transactions (printr_transfer, printr_transfer_token, printr_claim_fees) and manage encrypted wallets.
Sanitization: Sanitization is expected to be handled by the underlying MCP server implementation rather than the skill's instructions.

printr