OpenSpec

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill is coherent and purpose-aligned, with the main things to review being its global npm CLI install and its expected ability to change project files.

This skill appears safe for its stated purpose. Before installing, trust or pin the external npm CLI, use version control, review generated OpenSpec and `.claude/skills/` files, and confirm important implementation or archive steps before accepting them.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The CLI behavior can change when the npm package updates, and the package runs with the user's normal local permissions when used.

Why it was flagged

The skill directs users to install an external npm CLI globally using `@latest`; this is central to the stated purpose, but it is an unpinned external dependency.

Skill content
npm install -g @fission-ai/openspec@latest
Recommendation

Install only if you trust the OpenSpec npm package; consider pinning a specific version for reproducible projects.

What this means

When invoked, the agent may change local project files and OpenSpec records as part of the requested development process.

Why it was flagged

The agent workflow includes writing project artifacts, implementing tasks, and archiving with confirmation bypass. This is expected for a development workflow, but it mutates repository state.

Skill content
Then write the artifact file to `openspec/changes/<name>/`. ... **Implement** tasks from `tasks.md`. ... `openspec archive <name> --yes`
Recommendation

Use version control and review generated tasks, implementation changes, and archive actions before accepting them in important projects.

What this means

Repository OpenSpec files may shape what the agent writes or prioritizes during planning and implementation.

Why it was flagged

Project-local schemas, templates, and config can inject instructions into artifact generation. This is part of the design, but those stored instructions can influence the agent if they come from an untrusted repository.

Skill content
`instruction` | AI instructions injected when creating the artifact ... Context and rules from `config.yaml` are injected alongside templates when generating artifacts.
Recommendation

Review OpenSpec schemas, templates, and config before relying on them in untrusted or newly cloned projects.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The project may retain Claude/OpenSpec integration files after setup, affecting later agent sessions in that project.

Why it was flagged

Setup can create persistent Claude integration files in the project. This is disclosed and aligned with the skill's purpose, but it changes future project-level agent behavior.

Skill content
openspec init --tools claude ... `.claude/skills/`          # Auto-generated Claude integration
Recommendation

Review generated `.claude/skills/` files and remove them if you do not want persistent project-level integration.