The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill requires a SEED_PHRASE environment variable to be set for the @indigoprotocol/cardano-mcp package. This is a highly sensitive mnemonic phrase used to derive private keys and access wallet funds. While necessary for the skill's primary function of querying private wallet balances, users should handle this secret with extreme caution.
[EXTERNAL_DOWNLOADS]: The skill installs the @indigoprotocol/cardano-mcp package via Node.js. This is a vendor-owned resource originating from the skill author 'IndigoProtocol' and is required to facilitate communication with the Cardano network.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via blockchain data. Asset names or metadata stored on-chain could contain malicious instructions that an agent might follow when processing wallet balances.
Ingestion points: Asset names and hex-encoded labels returned by the get_balances tool (documented in references/mcp-tools.md).
Boundary markers: None specified in the instructions for separating external blockchain data from system prompts.
Capability inventory: The skill is granted Read, Glob, and Grep capabilities (documented in SKILL.md), allowing the agent to read local files.
Sanitization: No explicit sanitization or validation of asset names is described before they are presented to the agent.

cardano-balances