Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Explore Maldives
v3.2.1Plan your Maldives paradise escape — overwater villas, crystal clear lagoons, world-class snorkeling, private island resorts, and romantic sunset cruises. Al...
⭐ 0· 56·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's name/description (Maldives travel planning) matches the runtime instructions (calls to a 'flyai' CLI for flights, hotels, POIs). Requiring a CLI client is reasonable for live booking data. However the skill references Alibaba/Fliggy and a parent 'flyai' repo while the package owner/source are unknown in the registry metadata — provenance is unclear and worth verifying.
Instruction Scope
SKILL.md mandates installing and executing an external CLI (npm i -g @fly-ai/flyai-cli) and that every data item must come from that CLI output. It also instructs writing an internal execution log (echo '...'>>.flyai-execution-log.json) if filesystem writes are available. For an instruction-only skill, directing automatic installation and filesystem writes increases operational risk and should be reviewed before running.
Install Mechanism
There is no install spec in the registry bundle; instead the SKILL.md tells the agent/user to run npm i -g @fly-ai/flyai-cli. Installing a global npm package is a moderate-risk action because it executes third-party code on the host. The package namespace (@fly-ai) and the skill's registry metadata do not provide a verifiable homepage or trusted upstream link in this bundle, so the install target's trustworthiness is unknown.
Credentials
The skill declares no required env vars, credentials, or config paths — appropriate for a read-only travel query wrapper. That said, the runbook suggests persisting logs to a local file if available; while not a secret request, it introduces local persistence that users should be aware of.
Persistence & Privilege
always:false and agent-autonomy allowed (default) — normal. The only persistence behavior described is optional logging to .flyai-execution-log.json if filesystem writes are available, which is scoped to this skill's runbook but could create local artifacts.
Scan Findings in Context
[no-regex-findings] expected: Scanner found no code-level indicators because this is an instruction-only skill (no code files). Absence of findings is not proof of safety; the runtime instructions (installing/executing an external CLI) are the primary surface to review.
What to consider before installing
This skill appears to do what it claims (real-time travel results) but requires installing and running an external npm CLI (@fly-ai/flyai-cli) whose origin isn't verifiable from the bundle. Before installing or allowing an agent to run it: 1) Check the npm package page and publisher identity for @fly-ai/flyai-cli and inspect its repository/homepage and recent releases; 2) Prefer manually installing the CLI in a sandbox or VM and inspecting its files/behaviour (or review the package source on GitHub) instead of allowing an autonomous agent to run npm i -g; 3) Be aware the runbook may create .flyai-execution-log.json in the working directory — review any logs for sensitive data; 4) If you cannot confirm the CLI is from a trusted vendor (Alibaba/Fliggy) or review its code, do not install the package system-wide. If you want minimal risk, ask the skill author for a verified upstream repo or an official SDK/package link before proceeding.Like a lobster shell, security has layers — review code before you run it.
latestvk979qm5rdgzn8a8s9xa7v06ked84hjhr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.