Edit features with the Editor component/widget, configure forms, manage subtypes, handle attachments, and work with branch versioning.
67
60%
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/5.0/skills/arcgis-editing/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: 0.80). The skill's required workflows and examples explicitly create FeatureLayer instances from external service URLs (e.g., "https://services.arcgis.com/.../FeatureServer/0"), use CDN imports, and call methods like queryRelatedFeatures and queryAttachments so the agent will fetch and interpret untrusted public service data and attachments that can influence form visibility, edits, and subsequent actions.
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: 0.80). The skill's example runtime includes loading the ArcGIS JS API from the CDN (e.g., https://js.arcgis.com/5.0/ and https://js.arcgis.com/5.0/map-components/), which fetches and executes remote JavaScript at page load and is required for the components/$arcgis.import() usages.
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.