The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a configuration script, scripts/configure-keyapi-auth.mjs, which modifies sensitive system configuration files to store authentication tokens. Specifically, it writes export commands to user shell profiles including .bashrc, .zshrc, .bash_profile, .profile, and PowerShell profiles. This behavior is used to ensure the KEYAPI_TOKEN environment variable persists across different user sessions.
[DATA_EXFILTRATION]: The scripts/keyapi-api.mjs script transmits the authentication token and marketplace query data to external endpoints. The KEYAPI_TOKEN is included in the Authorization header for all requests directed to https://api.keyapi.ai.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by dynamically parsing remote documentation to guide its execution logic.
Ingestion points: The skill fetches content from https://docs.keyapi.ai/llms.txt and individual endpoint documentation pages in the https://docs.keyapi.ai/en/amazon/ path.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the fetched remote documentation.
Capability inventory: The skill has capabilities for network communication via fetch and filesystem operations (reading and writing files) through its included Node.js scripts.
Sanitization: The skill uses regular expressions and JSON.parse to extract endpoint details from the remote documentation but does not perform content validation beyond structural parsing.

keyapi-amazon