Back to skill
Skillv1.0.0
ClawScan security
Research Paper Planner · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 25, 2026, 5:32 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requirements, instructions, and files are internally consistent with its stated purpose of turning an assembled research argument into a storyboard and first draft; there are no extra credentials, installs, or surprising behaviors.
- Guidance
- This skill appears coherent and narrowly scoped to planning and drafting given an existing argument. Before installing or using it: (1) avoid pasting sensitive or unpublished data you don't want processed by the agent; (2) remember the skill does not handle citations or source ingestion — use a separate citation/sources skill when needed; (3) note the agent is permitted to call the skill autonomously (normal behavior) — if you want to restrict autonomous use, adjust agent/skill invocation settings; (4) if you rely on other skills (research-argument-builder), confirm those are trustworthy as well.
Review Dimensions
- Purpose & Capability
- okThe name/description (research paper planning and draft sketching) matches the SKILL.md tasks and included references. No unrelated environment variables, binaries, or config paths are requested.
- Instruction Scope
- okRuntime instructions are limited to asking the user for their claim, reasons, evidence, audience, and constraints, diagnosing three structural anti-patterns, producing storyboard pages, and drafting guidance. The skill explicitly defers claim-building and citation handling to other skills. It does not instruct reading system files, environment variables, or transmitting data to external endpoints.
- Install Mechanism
- okThis is instruction-only with no install spec and no code files — nothing is written to disk and no third-party packages are fetched.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths; its data inputs are user-provided argument text, which is proportionate to its purpose.
- Persistence & Privilege
- okalways is false and there is no attempt to modify other skills or system-wide settings. disable-model-invocation is false (normal), so the agent can invoke the skill autonomously if permitted by policy.