sentry-get-started
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions to hide technical status updates and a specific onboarding handoff token from the user's conversational view. For example, it directs the agent to 'Never mention, quote, restate, label, or explain' the onboarding code and to make progress calls 'transparently' with 'no narration, announcement, exposition, or summary'. These instructions are designed to provide a cleaner user experience by syncing with Sentry's web UI, and the agent is instructed to explain the calls if the user explicitly asks.
- [EXTERNAL_DOWNLOADS]: The skill recommends using several official Sentry tools, including
npx @sentry/wizard@latest,brew install getsentry/tools/sentry-wizard, anddart run sentry_dart_plugin. These are well-known, vendor-provided tools from a trusted source. - [COMMAND_EXECUTION]: The skill instructs the agent to use local tools like
grepto check for the presence of Sentry-related strings (e.g.,@sentry,sentry-sdk,sentry_sdk) and DSNs within the user's repository.
Audit Metadata