jira-ticket-writing
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied content and external issue data to generate ticket summaries and descriptions, which creates a potential surface for indirect prompt injection.
- Ingestion points: Processes user requests for drafting/editing and reads existing issue data from the Jira API (SKILL.md).
- Boundary markers: Lacks explicit delimiters for interpolated user content, but provides strict instructional boundaries for the agent (Operating Boundary section).
- Capability inventory: Has the ability to create or update Jira issues via an API configuration (SKILL.md).
- Sanitization: Enforces Atlassian Document Format (ADF) schema validation but does not explicitly describe content sanitization or filtering.
- Mitigation: The skill mandates that the agent must return a draft by default and requires explicit user confirmation before performing any mutation, which serves as a critical human-in-the-loop safety check.
Audit Metadata