PlanSuite

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

Users relying on provenance should know the embedded metadata appears stale or inconsistent.

Why it was flagged

The package-internal metadata differs from the supplied registry metadata, which lists a different owner ID and version 0.1.3. Because the skill has no installer or code, this is a provenance note rather than a behavior concern.

Skill content
"ownerId": "local-author", "slug": "plansuite", "version": "0.1.0"
Recommendation

If publisher identity or exact version provenance matters, verify the package source before installing.

What this means

Project details may remain in local Markdown files and be used as context in later work.

Why it was flagged

The skill deliberately stores task plans, progress, findings, decisions, commands, and rollback steps in persistent local files so they can be reused across sessions.

Skill content
不要把这三份写到聊天里:写到文件,才能恢复/续跑。
Recommendation

Keep the generated files in the intended project directory, avoid writing secrets into them, and review them before resuming a task.

What this means

A separate execution session may receive plan context and perform implementation steps under the user-approved plan.

Why it was flagged

The workflow may delegate execution to a separate session. This is disclosed and purpose-aligned, but it creates a context boundary users should understand.

Skill content
建议用 `sessions_spawn` 开一个隔离执行会话(避免污染主会话上下文)。
Recommendation

Only spawn an execution session after reviewing the finalized plan, and review the spawned session's proposed changes and results.