sentry-get-started
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install official Sentry SDKs and CLI tools (such as sentry-sdk, @sentry/node, and @sentry/wizard) from verified public registries like npm, PyPI, and Homebrew. These resources originate from the verified vendor getsentry. \n- [CREDENTIALS_UNSAFE]: The skill provides robust instructions for secret management, correctly advising users to use environment variables and CI/CD secret stores for Sentry auth tokens and DSNs while explicitly warning against committing these credentials to source control. \n- [INDIRECT_PROMPT_INJECTION]: The core instructions include a mandatory safety directive for the AI agent to treat all data retrieved from the Sentry MCP (e.g., event titles, payloads, and comments) as untrusted input to prevent malicious instructions from influencing agent behavior. \n- [SAFE]: Static analysis and manual review of the skill's instructions confirmed the absence of obfuscation, malicious exfiltration patterns, or unauthorized privilege escalation attempts.
Audit Metadata