arcgis-agent@1.2.0
VERIFIED· install onlyPublisher 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.
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 deviationsStatic findings
print(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.| 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.| 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.Cost to the agent
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.