Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
food-travel
v1.0.0Plan food-driven travel experiences — recommend best cities for a dish or cuisine, generate city food maps with meal-by-meal restaurant routes, and build com...
⭐ 0· 27·0 current·0 all-time
by@zzzilin
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 (food-driven travel planning) aligns with the actions described (web searches, flights/hotels/POI lookups, building itineraries). However, it relies heavily on a 'flyai' service/CLI for logistics even though the skill metadata declares no required binaries or primary credentials, which is a mismatch.
Instruction Scope
SKILL.md instructs the agent to perform web searches and to run specific flyai CLI commands (search-flight, search-hotel, search-poi, keyword-search) and to always include booking links and images. There is no guidance about authentication, rate limits, or allowed data sources. Asking the agent to always include booking links/images could cause it to surface third-party URLs and images automatically. The instructions also assume availability of the flyai CLI and its realtime results but do not declare or limit how credentials or API responses should be handled.
Install Mechanism
This is an instruction-only skill (no install spec) which is low-risk in itself. However, the runtime expects an external 'flyai' CLI/tool to be present; the skill metadata does not declare that binary or provide an install step. That mismatch is a practical problem (will fail at runtime) and an incoherence to surface to users.
Credentials
The skill declares no environment variables or credentials, yet it depends on external realtime services (fly.ai) that typically require authentication. If flyai requires API keys/tokens, the skill should declare them; the absence suggests missing metadata and could lead to the agent attempting to call external services without clear credential handling. No unrelated secrets are requested, which is good, but the lack of declared auth is a gap.
Persistence & Privilege
always is false and there are no config path or persistence requests. The skill can be invoked by the model (default) which is normal for skills; there is no elevated or permanent privilege requested.
What to consider before installing
This skill appears to do what it says (plan food-first travel) but has an important inconsistency: its runtime instructions call a 'flyai' CLI and expect real-time booking/search results, yet the skill metadata declares no required binary nor any credentials. Before installing or enabling: 1) Confirm whether your agent environment provides a 'flyai' tool or built-in integration — if not, the skill will fail or the agent may try other means to fetch data. 2) Ask the skill author to declare required binaries and any API keys/environment variables (and to explain how credentials are stored). 3) Consider whether you are comfortable the skill will include third-party booking links/images (these may contain tracking/affiliate parameters); if not, request an option to omit external links. 4) If you do not want the agent to autonomously call external services, keep autonomous invocation off for this skill or review its runtime logs. If the author supplies the missing binary/credential declarations and explains auth handling, re-evaluate — that would move this toward benign.Like a lobster shell, security has layers — review code before you run it.
latestvk97fqmjb3srezhbyf6218bastd843ey0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.