Back to skill
Skillv1.0.0
ClawScan security
City Of London · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 3:05 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that provides static informational content about London; its requirements and instructions are coherent with that purpose and it does not request credentials, install software, or perform unexpected actions.
- Guidance
- This skill appears safe from a security perspective: it is just static informational content and asks for no credentials or installs. Consider that provenance is unknown (no homepage, anonymous owner ID) so verify any factual claims (GDP, rankings, dates) if you need authoritative data. If you care about source credibility, prefer skills or data that cite official sources or well-known publishers.
Review Dimensions
- Purpose & Capability
- okThe skill's name/description (London as a financial/cultural hub) matches the SKILL.md informational content. There are no requested binaries, env vars, or config paths that are unrelated to delivering city information. Minor mismatch: registry name 'City Of London' vs SKILL.md 'London' is cosmetic only.
- Instruction Scope
- okSKILL.md contains only static content and 'read_when' triggers for relevant user prompts (finance, competitiveness, Brexit effects). It does not instruct the agent to read files, access credentials, call external endpoints, or transmit data elsewhere.
- Install Mechanism
- okNo install spec or code files are present; the skill is instruction-only so nothing is written to disk or fetched during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. No sensitive access is requested and nothing in the instructions attempts to access hidden environment data.
- Persistence & Privilege
- okFlags show default behavior (not always: true). The skill is user-invocable and may be invoked autonomously per platform defaults, which is expected for a harmless informational skill.