The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external APIs which could theoretically contain malicious instructions designed to influence the agent.
Ingestion points: The skill fetches data from external endpoints via curl in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded text are provided for the API output.
Capability inventory: The skill utilizes web_search and curl to interact with external sources.
Sanitization: No sanitization or validation of the API response content is performed beyond checking for JSON format.
[COMMAND_EXECUTION]: The skill uses the curl utility to validate the responsiveness and data structure of external API endpoints. The usage is restricted to fetching the first 500 characters of the response, which is a safe way to inspect headers and initial body content without executing remote scripts.

api-research