openspec-new-change

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the openspec CLI to perform operations such as creating new changes and retrieving artifact instructions. These actions are performed via shell commands.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface where user input is used to determine command arguments.
  • Ingestion points: Change names and descriptions provided by the user in the initial step.
  • Boundary markers: The instructions suggest using double quotes to wrap the kebab-case name in shell commands.
  • Capability inventory: The skill is capable of executing various openspec CLI subcommands which interact with the local filesystem.
  • Sanitization: The skill includes instructions for the agent to validate the kebab-case format of names and verify the existence of change directories before proceeding.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:23 PM