The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a Python script (scripts/sentry.py) to interact with the Sentry API. The command execution is limited to pre-defined subcommands (issues, issue, event-latest, report) and follows standard patterns for CLI tools.
[CREDENTIALS_UNSAFE]: The skill properly handles sensitive information by instructing users to set SENTRY_AUTH_TOKEN as an environment variable. The code specifically includes a check to discourage passing the token via CLI arguments to avoid leaking it to shell history.
[EXTERNAL_DOWNLOADS]: The script makes network requests to sentry.io (or a user-defined SENTRY_BASE_URL) using Python's urllib. These requests are necessary for the skill's primary function of fetching error logs and events from the Sentry service.
[DATA_EXFILTRATION]: While the skill retrieves sensitive error data and stack traces, it only pulls this information into the local environment for triage and debugging. There are no patterns indicating that this data is being forwarded to unauthorized third-party domains.

sentry-debugger