The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx starkfi@latest to fetch and execute the StarkFi CLI package from the npm registry at runtime. While npm is a well-known service and the package corresponds to the author's identity, this pattern involves executing code from an external source during operation.
[COMMAND_EXECUTION]: The skill is granted permission to execute bash commands using npx to perform configuration updates and query transaction statuses on-chain.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its interaction with untrusted external data.
Ingestion points: Data is ingested into the agent context from the output of npx starkfi@latest tx-status and npx starkfi@latest config get-rpc (SKILL.md).
Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the skill to protect against malicious payloads in external data (SKILL.md).
Capability inventory: The skill has the capability to modify local configuration files and network settings via npx (SKILL.md).
Sanitization: There is no evidence of sanitization, validation, or escaping of the data returned by external tools before it is processed by the agent (SKILL.md).

config