The Agent Skills Directory

[COMMAND_EXECUTION]: Provides example curl commands for the user to manually verify API connectivity and fetch data using their local shell.
[DATA_EXFILTRATION]: Performs network requests to api.getxapi.com to retrieve Twitter data. These requests are directed to the official API of the service described in the skill and do not involve transmission of local sensitive data or credentials to unauthorized endpoints.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content from X/Twitter posts.
Ingestion points: Data is fetched from the GetXAPI search endpoint (https://api.getxapi.com/twitter/tweet/advanced_search) as documented in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands within the retrieved tweet data.
Capability inventory: The skill uses network operations (curl) to fetch data, but lacks dangerous local capabilities such as file system writing or direct shell execution of the retrieved data.
Sanitization: There is no mention of filtering or sanitizing the retrieved tweet text before it is summarized or incorporated into agent reports and drafts.

getxapi-connect