list-plans

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill includes PowerShell and Bash scripts intended for execution in a terminal to locate migration plans. These scripts are scoped to search for directories within the .github/modernize/ path that contain required files, such as plan.md and tasks.json.
  • Indirect Prompt Injection Surface: The skill processes local repository data by reading the first heading of discovered plan.md files to generate selection titles. This creates an ingestion point for external data from the workspace to be displayed in the agent's user interface.
  • Ingestion points: Content read from .github/modernize/<folder>/plan.md in the workspace.
  • Boundary markers: No explicit delimiters are used when processing the extracted titles.
  • Capability inventory: Terminal script execution for file discovery and subsequent file reading operations.
  • Sanitization: Basic string manipulation is applied to strip markdown formatting and specific prefixes from the extracted titles.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 09:54 PM