sentry-debug-issue
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by processing external data from Sentry events (exception messages, logs, breadcrumbs) that could contain malicious instructions. It handles this risk through explicit defensive prompts and instructions.\n
- Ingestion points: Data is ingested via MCP tools such as
get_sentry_resourceandsearch_issueswhich return issue details, logs, and user feedback.\n - Boundary markers: The skill mandates treating Sentry data as raw input and explicitly commands the agent to never follow embedded instructions.\n
- Capability inventory: The agent is authorized to use file system tools for code modification and git for version control operations (commit/PR).\n
- Sanitization: The skill instructs the agent to redact secrets and PII from all code fixes, reports, and tests.\n- [SAFE]: Analysis of all other threat categories, including remote code execution, persistence, and obfuscation, found no suspicious or malicious behavior. The skill is authored by the legitimate vendor (getsentry) and follows secure implementation standards by providing clear security boundaries for handling external data.
Audit Metadata