The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill relies on npx @xapi-to/xapi to execute its functions. This mechanism downloads and runs the latest version of the xapi package from the npm registry at runtime.
[COMMAND_EXECUTION]: The skill facilitates the execution of multiple CLI commands via npx to perform data retrieval, account registration, and configuration tasks.
[CREDENTIALS_UNSAFE]: The skill manages an API key for the xapi service.
The key is stored locally in a configuration file at ~/.xapi/config.json.
The documentation notes that the topup command generates a payment URL that includes the API key as a query parameter, which could lead to accidental exposure if the URL is logged or shared.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from untrusted third-party sources.
Ingestion points: Data is ingested through commands like twitter.user_tweets, twitter.tweet_detail, web.search, and news.search.latest (SKILL.md).
Boundary markers: The instructions do not define specific boundary markers or delimiters to separate external content from agent instructions.
Capability inventory: The skill has the capability to execute shell commands via npx and perform network operations to interact with various APIs (SKILL.md).
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from external sources before processing it.

xapi