sentry-debug-issue
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill includes a dedicated 'Security' section that explicitly instructs the agent to treat all data returned from the Sentry MCP as untrusted, Controllable by potential attackers.
- [SAFE]: It mandates specific defenses against indirect prompt injection by instructing the agent to never follow instructions embedded within error messages, breadcrumbs, or comments.
- [SAFE]: The instructions protect against data exposure by requiring the agent to redact secrets, passwords, and PII found in event data and to avoid pasting raw external values directly into code or test fixtures.
- [SAFE]: The skill relies on authenticated vendor-provided MCP tools (Sentry) for data retrieval and issue management, minimizing the surface area for unauthorized external access or code execution.
Audit Metadata