The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it instructs the agent to ingest and act upon data from external Jira issues and comments.
Ingestion points: The agent retrieves potentially attacker-controlled content via JIRA_GET_ISSUE (descriptions) and JIRA_LIST_ISSUE_COMMENTS (comment bodies).
Boundary markers: No specific delimiters or "ignore previous instructions" warnings are provided to prevent the agent from obeying commands embedded in Jira issue data.
Capability inventory: The agent has significant write capabilities, including JIRA_CREATE_ISSUE, JIRA_EDIT_ISSUE, JIRA_ASSIGN_ISSUE, and project role management, which could be abused if an injection is successful.
Sanitization: There are no instructions for sanitizing or validating the content retrieved from Jira before processing.
[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint at https://rube.app/mcp. This third-party service acts as a proxy for Jira operations and handles authentication via OAuth.

jira-automation