Sentry Error Triage

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This Sentry skill fits its purpose, but needs review because it can use a Sentry token to change monitoring state and upload project artifacts without clear approval guardrails.

Install only if you want an agent operating against your Sentry account. Use the narrowest Sentry token scopes possible, keep the token out of chats/logs/history, review stack traces and source maps for sensitive data, and require explicit approval before resolving, ignoring, assigning, bulk-updating, creating releases/deploys, or uploading artifacts.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs users to export and use a long-lived Sentry auth token and then query event/issue data, but it omits explicit guidance about securely storing credentials, least-privilege scoping, shell history leakage, and the sensitivity of stack traces/breadcrumbs that may contain user or system data. In an agent setting, this increases the chance that secrets are mishandled or that sensitive telemetry is retrieved and transmitted without adequate operator awareness.

VirusTotal

65/65 vendors flagged this skill as clean.