openspec-bulk-apply-change

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands via git and the openspec CLI to list changes, check status, and manage isolated git worktrees for parallel execution.
  • [PROMPT_INJECTION]: Indirect injection surface: The skill ingests data from external sources including CLI JSON output (openspec list, openspec status), contextFiles, and tasks artifacts to inform subagent dispatch.
  • Ingestion points: JSON output from openspec commands and local project files (SKILL.md, Step 3).
  • Boundary markers: Not explicitly defined in the subagent prompt instructions to separate ingested data from agent commands.
  • Capability inventory: Git worktree creation, subagent dispatch, and CLI tool execution (openspec, git).
  • Sanitization: No explicit sanitization or validation mentioned for the content of contextFiles or tasks artifacts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:12 AM
Security Audit — agent-trust-hub — openspec-bulk-apply-change