The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and installs several packages including @orpc/experimental-publisher, ioredis, and @upstash/redis. These are well-known libraries or vendor-specific resources for the oRPC project.
[PROMPT_INJECTION]: The skill establishes an architectural pattern for processing external event payloads from sources like Redis or Cloudflare. This creates a surface for indirect prompt injection if payloads contain instructions targeting the agent.
Ingestion points: Event payload yielded in SKILL.md asynchronously.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are demonstrated in the snippets.
Capability inventory: The skill yields event data directly into the agent's processing context.
Sanitization: No explicit sanitization of the event data is shown in the usage examples.
[SAFE]: No evidence of credential theft, obfuscation, or unauthorized network activity was found.

oRPC Publisher