plan-to-tickets
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands (mkdir, echo, awk, grep) to manage local state files within a .plan-import directory. It also recommends using Python scripts to process large JSON tool-results files that exceed token limits, which is a standard pattern for handling large-scale data imports in this environment.
- [DATA_EXFILTRATION]: The skill facilitates the transfer of project data from local documents to external task management platforms (ClickUp, Linear, Jira, Asana, Notion, and GitHub Projects) via official Model Context Protocol (MCP) integrations. This data movement is integral to the skill's functionality and is initiated based on explicit user requests.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of user-provided planning documents.
- Ingestion points: Ingests markdown or text files containing implementation plans, design docs, or task lists.
- Boundary markers: None explicitly defined for isolating the input data; however, the skill mandates a 'readiness check' to ensure the input is a structured plan rather than generic prose.
- Capability inventory: The skill uses local file system access, shell command execution, and a wide array of MCP tools for creating, updating, and deleting tickets on external platforms.
- Sanitization: There are no explicit sanitization steps for input data before it is transmitted to external APIs or used in local shell processing.
Audit Metadata