Back to skill
Skillv1.0.0
ClawScan security
Goal Clarifier · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 9, 2026, 2:10 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, required resources, and metadata are coherent with its stated purpose (clarifying user goals) and it does not request credentials, install code, or access system files.
- Guidance
- This skill appears coherent and low-risk: it only changes how the agent asks questions and produces a brief. Before installing, consider: (1) provenance — the owner and homepage are missing, so if provenance matters to you, prefer skills with identifiable maintainers; (2) implicit invocation — the skill is allowed to trigger automatically on matching prompts, so disable implicit invocation if you don't want it to interrupt flows; (3) review the SKILL.md yourself to ensure its question style fits your workflow. If those points are acceptable, the skill is safe to use for clarifying goals but remember it only guides conversation — it does not perform actions or access secrets.
Review Dimensions
- Purpose & Capability
- okThe name and description ('Goal Clarifier') match the SKILL.md: it only asks the agent to ask questions and produce a six-part brief. There are no unrelated environment variables, binaries, or config paths requested. (Note: the package has no homepage and an unknown owner ID, which is a provenance/traceability issue but does not affect capability alignment.)
- Instruction Scope
- okThe runtime instructions are limited to conversational behavior: detect solution-shaped requests, ask targeted follow-ups, and emit a constrained brief. The SKILL.md does not instruct reading files, environment variables, network endpoints, or performing external actions.
- Install Mechanism
- okThis is an instruction-only skill with no install spec and no code files to execute; therefore it has minimal disk/execution risk.
- Credentials
- okThe manifest declares no required environment variables, credentials, or config paths. The instructions also do not reference any secrets or external service credentials.
- Persistence & Privilege
- notealways is false (normal). The agents/openai.yaml sets policy.allow_implicit_invocation: true, which permits implicit invocation when triggers match; this is reasonable for a conversational clarifier but you may prefer to restrict implicit triggering depending on your policy.