The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing the ai-news CLI tool to perform all its core functions, including article retrieval, URL analysis, and integration management.
[EXTERNAL_DOWNLOADS]: The skill documentation explicitly instructs users to install an external package, ai-news-cli, via the npm package manager.
[REMOTE_CODE_EXECUTION]: The skill features dynamic logic loading where commands are fetched from the developer's server (ai-news.stringzhao.life) at runtime. This allows the remote server to influence the agent's available actions and behavior dynamically.
[PROMPT_INJECTION]: The skill processes data from external URLs via the url:analyze command and fetches remote article summaries. This creates a surface for indirect prompt injection if the ingested content contains instructions designed to manipulate the agent's behavior.
Ingestion points: External URLs submitted via url:analyze and article content fetched via articles:list and articles:summary (SKILL.md).
Boundary markers: No explicit boundary markers or instruction-ignoring delimiters are defined for the ingested content.
Capability inventory: The agent can execute shell commands via the CLI, install packages, and send data to remote servers.
Sanitization: There is no evidence of sanitization or validation of the content returned by the external analysis or news services.
[DATA_EXFILTRATION]: The skill transmits user-supplied URLs to a remote API for analysis and supports the configuration of external webhooks (Flomo), which can be used to route data to third-party endpoints.

ai-news