jira-create-ticket
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses organizational communication data from Slack and Fireflies transcripts to gather context for ticket creation. This data is processed to generate drafts and then transmitted to the user's Atlassian Jira instance via the Atlassian MCP.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted content from Slack messages and meeting transcripts.
- Ingestion points: Slack channel history and Fireflies meeting transcripts (SKILL.md, Step 2).
- Boundary markers: No explicit delimiters or boundary markers are defined for the interpolation of external text into the ticket drafting prompt.
- Capability inventory: The skill can search for, fetch, and create Jira tickets (Epics, Stories, Tasks, Bugs) using the Atlassian MCP.
- Sanitization: Security is managed through a human-in-the-loop approval requirement in Step 6, which prevents the autonomous creation of tickets without user verification of the generated content.
Audit Metadata