The Agent Skills Directory

[DATA_EXFILTRATION]: The skill provides instructions to access sensitive file paths, specifically searching for the AGENT_READY_API_KEY within .env and other local configuration files using grep. This data is used solely to authenticate requests to the vendor's API.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to https://agent-ready.dev/api/v1/scans and https://agent-ready.dev/api/v1/ask to submit scan jobs and retrieve audit results. These are official endpoints for the skill's documented functionality.
[COMMAND_EXECUTION]: The instructions utilize several shell commands, including grep, cut, curl, and jq, for secret management, network communication, and data parsing.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8c) because it processes and summarizes audit results from an external API.
Ingestion points: Site audit results and check messages are retrieved as JSON from https://agent-ready.dev/api/v1/scans/{id}.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when summarizing findings.
Capability inventory: The skill uses curl to perform network operations and shell utilities for environment management.
Sanitization: No explicit sanitization or validation of the text content within the scan results is mentioned before the agent summarizes the data for the user.

agent-ready-api