Back to skill
Skillv0.1.0
ClawScan security
Reasoning Answer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 16, 2026, 5:59 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This instruction-only skill is internally consistent with its stated purpose (producing reasoning answers with numbered clickable citations) and requests no installs, secrets, or elevated privileges.
- Guidance
- This skill is instruction-only and asks for no credentials or installs, so it appears safe from a permissions perspective. Before installing, consider: (1) whether your agent/runtime supports the exact clickable footnote format ([[1]](URL)) the skill mandates, since that affects output rendering; (2) template variables like $DATE must be substituted correctly by your environment; and (3) if the agent will fetch web search results to populate citations, review how those searches are performed (privacy, trusted search sources). No regex scan findings were produced by the static scanner.
Review Dimensions
- Purpose & Capability
- okName/description match the content of SKILL.md: instructions focus on producing reasoning-style answers and formatted citations; no unrelated credentials, binaries, or installs are requested.
- Instruction Scope
- okRuntime instructions are narrowly scoped to language, date template variables, and citation formatting; they do not request reading files, environment variables, or transmitting data to unexpected endpoints.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only, so nothing is written to disk or fetched during install.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths; requested template variables are reasonable for runtime substitution.
- Persistence & Privilege
- okalways is false and default agent invocation is allowed (normal). The skill does not request persistent/system-wide changes or access to other skills' configs.