Interactive map tools including swipe comparison, measurement, identify, and routing. Use for layer comparison, distance/area measurement, and navigation services.
70
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./contexts/4.34/skills/arcgis-map-tools/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 0.70). The skill explicitly calls external ArcGIS REST endpoints and arbitrary layer URLs (e.g., identify.identify(identifyURL) using "https://sampleserver6.arcgisonline.com/...", route.solve(routeUrl) using "https://route-api.arcgis.com/...", find.find(findUrl), and TileLayer({url: "..."}) in SKILL.md) and then programmatically reads and acts on the returned feature/directions/attribute data (popups, route geometry, print outputs), which means untrusted public service responses could influence tool behavior.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Potentially malicious external URL detected (high risk: 0.70). The Complete Example loads and executes external JavaScript at runtime that the skill depends on (e.g., https://js.arcgis.com/calcite-components/3.3.3/calcite.esm.js, https://js.arcgis.com/4.34/, and https://js.arcgis.com/4.34/map-components/), so these URLs are runtime dependencies that execute remote code.
d84407b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.