The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill downloads a JavaScript file (call.mjs) from https://fittings.sh/skill/call.mjs and executes it using Node.js. This mechanism allows remote code to be run in the agent's environment, though it originates from the skill's own vendor domain.
[CREDENTIALS_UNSAFE]: The instructions direct users to set a sensitive private key in an environment variable (FITTINGS_PRIVATE_KEY). While the skill advises using a throwaway wallet, this pattern exposes cryptographic secrets to the local environment and any processes that can read it.
[COMMAND_EXECUTION]: The skill uses shell commands like curl and node to fetch external resources and perform API calls, including the execution of the downloaded call.mjs script.
[EXTERNAL_DOWNLOADS]: The skill fetches a script from https://fittings.sh/skill/call.mjs at runtime. While this is a vendor-owned resource, it introduces a dependency on the availability and integrity of the remote file.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the address field which is then processed and passed to an external API.
Ingestion points: The address field in the API call provided in SKILL.md.
Boundary markers: None found. There are no delimiters or instructions to ignore embedded commands within the address data.
Capability inventory: The skill has the capability to write files (curl -sO), execute code (node), and perform network operations.
Sanitization: No evidence of input sanitization or validation is present in the skill instructions.

fittings-census-address-geographies