triage-frontend-issues
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill enforces a strict human-in-the-loop model, requiring explicit user approval before any issue status mutations are performed.
- [SAFE]: Operations are strictly restricted to the sentry/javascript project and the archive status (ignored) with the untilEscalating mode, preventing unauthorized changes or privilege escalation within Sentry.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Sentry issue titles and stack traces which could contain malicious strings. However, the risk is minimized by the skill's specific classification heuristics and the requirement for a human to verify the triage plan.
- [COMMAND_EXECUTION]: The skill uses vendor-specific MCP tools to interact with the Sentry API. The use of these tools is transparently documented and limited to the defined triage workflow.
Audit Metadata