jira-automation
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server located at https://rube.app/mcp. This establishes a dependency on remote infrastructure that is managed outside the skill's own code and provides the core logic for the Jira integration.- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by ingesting and processing data from an external Jira environment.
- Ingestion points: The agent reads untrusted data (summaries, descriptions, and comments) through tools like JIRA_GET_ISSUE and JIRA_LIST_ISSUE_COMMENTS as described in SKILL.md.
- Boundary markers: There are no instructions or patterns provided to use delimiters or ignore sequences when processing these external fields.
- Capability inventory: The skill provides significant modification capabilities, including JIRA_CREATE_ISSUE, JIRA_EDIT_ISSUE, JIRA_ADD_COMMENT, and JIRA_MOVE_ISSUE_TO_SPRINT, which could be abused if an injection is successful.
- Sanitization: The skill does not describe any sanitization, validation, or filtering of the ingested Jira content before it is processed by the agent.
Audit Metadata