jira-issues
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation references the
@anthropic/create-mcp-serverpackage, which originates from a trusted organization. - [COMMAND_EXECUTION]: The skill provides shell commands for environment configuration and tool installation during setup.
- [DATA_EXFILTRATION]: Performs network requests to Atlassian's Jira API endpoints for legitimate issue management tasks.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through its interaction with external Jira issue data. Ingestion points: Data is retrieved via the
search_issuesandtransition_issuefunctions inSKILL.md. Boundary markers: No delimiters or ignore-embedded-instruction warnings are present. Capability inventory: The skill can perform network operations to create or modify issues. Sanitization: No sanitization of external content is shown in the provided code snippets.
Audit Metadata