jira
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from Jira issues which creates a surface for indirect prompt injection.
- Ingestion points: Data is ingested from external Jira issue fields such as summaries and descriptions via
jira.issue()andjira.search_issues()as demonstrated in the Python snippets inSKILL.md. - Boundary markers: No boundary markers or instructions to ignore embedded commands are included in the instructions or issue templates.
- Capability inventory: The skill allows for significant actions including issue creation and updates (
create_issue,update), workflow transitions (transition_issue), and execution of platform-specific CLI commands (/jira-create,/atlassian-sync). - Sanitization: The documentation does not specify any sanitization or validation of the content retrieved from Atlassian's APIs before it is processed by the agent.
Audit Metadata