Skills/ClawHub/travel-frog

travel-frog@1.0.0

CAUTION· static only

Publisher claims: "A travel frog that autonomously explores the world, sends postcards, and takes photos." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher nibbinnone · publishing for 258 daysInstalls 1,158Last detonated 20 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Fake instruction boundary tagtemplates/TOOLS.md:20 · Fake instruction boundary tag · informational: not an instruction file--prompt "<prompt>" --filename "$HOME/.openclaw/media/trip_<NNN>_<phase>.png" --resolution 1KFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:185 · File type combined with upload action — agent may exfiltrate local data files- `postcard` 和 `photo` 都会归档到 `collections.json` 的 `postcards` 数组(带 `type` 字段区分)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Fake instruction boundary tagtemplates/TOOLS.md:13 · Fake instruction boundary tag · informational: not an instruction file--prompt "<prompt>" --model gpt-image-1.5 --size 1024x1024 --count 1 \Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:255 · File type combined with upload action — agent may exfiltrate local data files- 归档数据:`travel-frog-data/collections.json`(持续增长,含 postcards/souvenirs/destinationsVisited)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/frog_engine.py:174 · File type combined with upload action — agent may exfiltrate local data fileslog.info(f"[migrate] collections.json written: {len(collections['postcards'])} postcards, {len(collections['souvenirs'])} souvenirs, {len(collections['destinationsVisited'])} destinations")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,222 tok
2 files · 11 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim nibbinnone: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim nibbinnonePropose a patch to the maintainer