openspec-onboard

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as an instructional guide for the OpenSpec onboarding process. It does not execute arbitrary shell commands, perform remote downloads, or access sensitive system files.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill is designed to ingest and analyze the user's local codebase to find improvement opportunities.
  • Ingestion points: User's local codebase (SKILL.md, Workflow section).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: File creation (/opsx:new) and implementation of changes (/opsx:apply).
  • Sanitization: Not explicitly mentioned in the skill instructions. This surface is a necessary component of the skill's primary function (codebase onboarding) and does not represent a malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:14 AM
Security Audit — agent-trust-hub — openspec-onboard