Back to skill
Skillv1.0.0
ClawScan security
Air Canada · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 25, 2026, 8:08 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about Air Canada; its declared purpose matches the instructions and it does not request credentials, installs, or access to system resources.
- Guidance
- The skill appears to be a simple informational document and poses minimal risk: it neither installs software nor asks for credentials. However, the source/homepage is unknown—if provenance matters to you (for e.g., publishing or business use), verify the author or prefer a skill with a known upstream. Also avoid providing any sensitive credentials or private files to the agent when invoking skills in general. If you later add functionality that fetches live data or integrates with APIs, expect new env vars or install steps and reassess at that time.
Review Dimensions
- Purpose & Capability
- okName and description promise corporate/history/background information about Air Canada; the SKILL.md contains only historical, business-model, and factual content consistent with that purpose.
- Instruction Scope
- okSKILL.md is read-only content (history, metrics, analysis) and the read_when triggers are contextual only. There are no instructions to run commands, read files, access environment variables, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill, so nothing is written to disk or executed during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; nothing requested is disproportionate to an informational skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable with normal model invocation allowed. This is appropriate for an informational skill and is not combined with broad access or installation behavior.