jira-automation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a third-party MCP server endpoint located at
https://rube.app/mcp. This introduces a dependency on external infrastructure managed by a vendor not included in the trusted providers list. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection attacks by ingesting untrusted content and executing actions based on it.
- Ingestion points: Untrusted data enters the agent context through tools like
JIRA_GET_ISSUE,JIRA_SEARCH_FOR_ISSUES_USING_JQL_POST, andJIRA_LIST_ISSUE_COMMENTSas described inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit warnings to the agent to disregard instructions that may be embedded within Jira issue descriptions or comments.
- Capability inventory: The skill includes tools for modifying the environment, such as
JIRA_CREATE_ISSUE,JIRA_EDIT_ISSUE,JIRA_ADD_COMMENT, andJIRA_ADD_USERS_TO_PROJECT_ROLE(referenced inSKILL.md). - Sanitization: There are no documented procedures for sanitizing, filtering, or validating the content retrieved from Jira before it is processed by the agent.
Audit Metadata