The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and retrieves update manifests and setup documentation from the developer's GitHub repository and the product's official website (threadwave.xyz).
[INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion point for user-supplied instructions which are then passed to specialized peer skills for execution, creating a routing path for potentially malicious embedded commands.
Ingestion points: User-provided automation requests and workflow selections processed in SKILL.md.
Boundary markers: Absent; the instructions explicitly require preserving exact user content and original request formatting during handoff to peer skills.
Capability inventory: The skill has the ability to invoke and pass data to several independent peer skills including twitter-post, twitter-reply, twitter-agent, and threadwave-preflight.
Sanitization: There is no evidence of input validation, filtering, or sanitization of the user-provided content before it is routed to the destination peer.

twitter-automation