openspec-new-change

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'openspec' CLI commands to manage project changes. This is the primary intended function and involves local tool interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where user-provided input is used to construct shell commands.
  • Ingestion points: The user's change name or project description is captured via the 'AskUserQuestion' tool or direct prompt.
  • Boundary markers: None explicitly present in the command string templates to delimit user input from the command structure.
  • Capability inventory: The skill uses the 'openspec' CLI for 'new change', 'status', 'instructions', and 'schemas' operations.
  • Sanitization: The skill includes instructions to the agent to 'derive a kebab-case name' and specifically 'If the name is invalid (not kebab-case), ask for a valid name' before executing the command.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 09:04 AM