Back to skill
Skillv1.0.0
ClawScan security
An interactive workflow structuring assistant that progressively clarifies and decomposes a vague process into a structured, executable workflow document. · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 5:14 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, required resources, and behavior align with its stated purpose and request no unexpected permissions or installs.
- Guidance
- This skill appears coherent and low-risk: it only contains conversational instructions and templates and asks for nothing extra. Before installing, avoid pasting sensitive secrets or credentials into any session, test the skill with non-sensitive examples, and confirm language preference (it follows the user's language). Note that the agent may invoke the skill when triggered by the listed phrases (normal behavior); if you prefer manual control, only enable the skill when needed.
Review Dimensions
- Purpose & Capability
- okThe name/description (interactive workflow structuring) matches the SKILL.md: progressive clarification, step-by-step drilling, templates and a handoff format. It does not request unrelated credentials, binaries, or system access.
- Instruction Scope
- okSKILL.md contains only conversational protocols, question templates, step rules, progress displays, and a handoff format. It does not instruct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec or code files that would be written to disk; this is an instruction-only skill, which minimizes installation risk.
- Credentials
- okNo required environment variables, credentials, or config paths are declared or referenced in SKILL.md. The skill does not ask for or depend on secrets.
- Persistence & Privilege
- okalways is false and there is no indication the skill modifies other skills or system settings. disable-model-invocation is default (false) which allows autonomous invocation — this is normal for skills and not by itself a red flag.