Skills/ClawHub/arcgis-agent

arcgis-agent@1.2.0

VERIFIED· install only

Publisher claims: "ArcGIS Agent - drive 2500+ ArcGIS Pro geoprocessing tools across 46 toolboxes (buffer/clip/intersect, slope/aspect/viewshed, kriging/IDW, hotspot/Moran's I, image analysis, GeoAI deep learning, multidimensional rasters, utility networks, geocoding and more) with natural language, via a local HTTP API. Use when the user asks for GIS/spatial analysis, ArcGIS automation, or arcpy operations. Requires Windows + ArcGIS Pro 3.x. 通过自然语言驱动 ArcGIS Pro 的 2500+ 个 arcpy 空间分析工具，覆盖 46 个工具箱（缓冲区/裁剪/相交、坡度/可视域、克里金/IDW、热点分析、影像分析、GeoAI 深度学习、多维栅格、公共设施网络、地址匹配等）。适用于 GIS 与空间分析、ArcGIS 自动化、arcpy 操作等需求。需要 Windows + ArcGIS Pro 3.x。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhaojj662 · publishing for 64 daysInstalls 526Last detonated 7d ago
$clawhub install arcgis-agent
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)scripts/server.py:236 · MCP server using network transport (SSE/HTTP) — data sent over networkprint(f"arcpy-mcp-server v{VER} | http://127.0.0.1:{PORT}", flush=True)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Destructive file system command detectedSKILL.md:200 · Destructive file system command detected| rm / oi / reviewer / wmx / transit / geoai | 14/6/5/18/8/12 | 正射/定向影像/质检/工作流/GTFS/GeoAI | 对应扩展 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:91 · Destructive file system command detected| rm / oi / reviewer / wmx / transit / geoai | 14/6/5/18/8/12 | Ortho mapping / oriented imagery / QA / workflow / GTFS / GeoAI | respective ext. |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,524 tok
1 file · 6 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.