Back to skill
Skillv1.0.0
ClawScan security
Trip Discover · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 1, 2026, 7:35 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requests and instructions are consistent with a travel recommendation assistant — it only needs web access and the agent's memory and does not ask for unrelated credentials or installs.
- Guidance
- This skill appears coherent and safe in terms of required access: it will perform web searches for current weather and destinations and may read the agent's memory to use your saved places. Before installing, consider: (1) Are you comfortable allowing the agent to access your saved places / memory? That may include personal travel history or wishlists. (2) The skill assumes 'From city: Delhi' by default — tell it your correct origin or confirm the assumption. (3) Recommendations use live web lookups and rough cost estimates; verify booking details and weather from authoritative sources before acting. If you want to limit privacy exposure, deny memory access or remove sensitive saved places first.
Review Dimensions
- Purpose & Capability
- okName and description match the instructions: the SKILL.md asks the agent to search the web, pick 2–3 destinations, provide travel time/cost/weather and prefer saved places. No unrelated binaries, env vars, or config paths are requested.
- Instruction Scope
- noteInstructions are narrowly scoped to recommending trips, comparing destinations, and checking saved places. They explicitly require web searches for current info and reading the agent's memory for saved destinations; both are coherent with the purpose but mean the skill will access network resources and personal memory data (saved destinations).
- Install Mechanism
- okNo install spec and no code files (instruction-only). Nothing will be written to disk or installed by the skill itself.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths — proportional to a recommendation-only skill. The only sensitive access indicated is reading agent memory for saved places, which is expected but should be understood by the user.
- Persistence & Privilege
- okalways is false and the skill does not request any elevated or persistent platform privileges or modifications to other skills. Normal autonomous invocation is allowed (platform default).