Back to skill
Skillv0.1.2
ClawScan security
Writing Inspiration · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 6, 2026, 3:17 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, files, and requirements are consistent with a writing‑inspiration helper and request no unexpected credentials, binaries, or installs.
- Guidance
- This skill appears coherent and low-risk: it only contains question-based prompts and frameworks for writing help, and requests no credentials or installs. Before installing, remember: the skill will prompt users to type content—do not paste sensitive personal data or secrets into the conversation. If a future version adds network endpoints, environment variables, or install steps, re-check those changes (any new credential requests or remote downloads would be a red flag).
Review Dimensions
- Purpose & Capability
- okName/description (writing inspiration for travel/TIL/general articles) match the SKILL.md and the included frameworks. No unrelated capabilities or requests are present.
- Instruction Scope
- okRuntime instructions are limited to asking iterative, scoped questions to elicit writing content and assembling answers into a draft. They do not instruct reading system files, accessing environment variables, or sending data to external endpoints.
- Install Mechanism
- okInstruction-only skill with no install spec and no code files beyond documentation; nothing is written to disk or downloaded during install.
- Credentials
- okNo required environment variables, credentials, or config paths are declared or referenced in the SKILL.md or reference files—proportionate for this purpose.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system-level privileges or modify other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other concerning requests.