build-sentry-macos-swift

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a development tool for integrating error monitoring and telemetry in a native macOS/Swift context with a strong focus on security best practices.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (grep, ls, find) in its discovery phase to profile the host project's structure, lifecycle, and distribution settings. These commands are read-only and used to inform the integration strategy.
  • [DATA_EXFILTRATION]: While the skill implements telemetry, it provides extensive documentation and code patterns for client-side scrubbing to prevent the exfiltration of sensitive data such as user content, file paths containing usernames, and IP addresses.
  • [CREDENTIALS_UNSAFE]: The skill correctly identifies the sensitivity of the Sentry authentication token and instructs developers to use secure storage methods like environment variables or gitignored configuration files rather than hardcoded secrets.
  • [PROMPT_INJECTION]: The skill includes a specific guardrail for the agent, instructing it to treat external event data and dashboard content as untrusted to mitigate potential indirect prompt injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:27 PM
Security Audit — agent-trust-hub — build-sentry-macos-swift