Open or resume a helpdesk ticket. Tickets are independent of projects.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Outsider free text can enter the LLM context via `duplo-helpdesk::Ticket_get_messages` (Step 5), which returns full ticket conversation history authored by other participants (e.g., end users/agents) and is then “read carefully” by the agent.
duplocloud/duplo-claude-plugin
6a46510
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.