$ ~/registry/skill/openai-curated-sentry

SKILL

sentry

Name: sentry
Author: OpenAI

Inspect Sentry issues, events, and recent production error health read-only.

Stars

★ 23,132

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 22.0k

Summary

The material and system checks indicate an open-source, highly adopted prompt-only skill with overall low risk. However, the README mentions Sentry CLI authentication and remote Sentry data access while the metadata declares no secrets and no remote endpoints, so this documentation-to-metadata mismatch should be verified under least-privilege assumptions.

CredentialsCaution

The metadata says no credentials are required, but the README explicitly mentions `sentry auth login` or setting `SENTRY_AUTH_TOKEN`. This indicates real usage may involve Sentry credentials; although it warns not to paste full tokens into chat, there is still credential exposure or misconfiguration risk.

Network egressCaution

The metadata lists no remote endpoints, but the README repeatedly describes using the Sentry CLI to query issues, events, and APIs, implying requests to Sentry services and outbound transfer of project/error-related data. There is no evidence of unrelated or unknown third-party endpoints, so this is a standard caution-level egress concern.

Code executionLow risk

The objective system checks mark this skill as prompt-only, indicating the skill itself does not directly execute local code or spawn processes. While the README includes examples for installing/running the Sentry CLI and `curl | bash`, those are documentation instructions rather than evidence of execution capability in the skill itself.

Data accessCaution

The README says the CLI auto-detects org/project from `.env` files, source code, config defaults, and directory names, which implies local project-context reading and access to Sentry issue/event data. The description emphasizes read-only queries, and there is no sign of write access or excessive authorization, but it still involves access to production error and event data.

Supply chainLow risk

The source is the open-source openai/skills repository on GitHub, with objective open-source status and strong community adoption (~22k stars), all of which are strong positive signals. Although the license is unspecified, maintenance status is unknown, and there is a minor README-to-metadata mismatch, the supply-chain risk is overall low due to auditable source code and a highly credible origin.

Recommendations

Verify whether the actual implementation is truly prompt-only; if it invokes the Sentry CLI, update the asset inventory with required credentials and remote endpoints.
Use a least-privilege Sentry token only, and avoid exposing full credentials in chat, logs, or terminal output.
Before using it in repositories containing sensitive DSNs, `.env` files, or production error data, confirm local read scope and output redaction behavior.
Do not blindly follow the README's `curl | bash` install path; prefer trusted package channels or verify installation scripts.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "sentry" skill from askskill:
1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/sentry/SKILL.md
2. Save it as ~/.claude/skills/sentry/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Sentry (Read-only Observability)

Quick start

If not already authenticated, ask the user to run sentry auth login or set SENTRY_AUTH_TOKEN as an env var.
The CLI auto-detects org/project from DSNs in .env files, source code, config defaults, and directory names. Only specify <org>/<project> if auto-detection fails or picks the wrong target.
Defaults: time range 24h, environment production, limit 20.
Always use --json when processing output programmatically. Use --json --fields to select specific fields and reduce output size.
Use sentry schema <resource> to discover API endpoints quickly.

If the CLI is not installed, give the user these steps:

Install the Sentry CLI: curl https://cli.sentry.dev/install -fsS | bash
Authenticate: sentry auth login
Confirm authentication: sentry auth status

Never ask the user to paste the full token in chat. Ask them to set it locally and confirm when ready.

Core tasks (use Sentry CLI)

Use the sentry CLI for all queries. It handles authentication, org/project detection, pagination, and retries automatically. Use --json for machine-readable output.

1) List issues (ordered by most recent)

sentry issue list \
  --query "is:unresolved environment:production" \
  --period 24h \
  --limit 20 \
  --json --fields shortId,title,priority,level,status

If auto-detection doesn't resolve org/project, pass them explicitly:

sentry issue list {your-org}/{your-project} \
  --query "is:unresolved environment:production" \
  --period 24h \
  --limit 20 \
  --json

2) Resolve an issue short ID to issue detail

sentry issue view {ABC-123} --json

Use the short ID format (e.g., ABC-123), not the numeric ID.

3) Issue detail

sentry issue view {ABC-123}

4) Issue events

sentry issue events {ABC-123} --limit 20 --json

5) Event detail

sentry event view {your-org}/{your-project}/{event_id} --json

6) AI-powered root cause analysis

sentry issue explain {ABC-123}

7) AI-powered fix plan

sentry issue plan {ABC-123}

Fallback: arbitrary API access

For endpoints not covered by dedicated CLI commands, use sentry api:

sentry api /api/0/organizations/{your-org}/ --method GET

Use sentry schema to discover available API endpoints:

sentry schema issues

Inputs and defaults

org_slug, project_slug: auto-detected by the CLI from DSNs, env vars, and directory names. Override with positional {your-org}/{your-project} if auto-detection fails.
time_range: default 24h (pass as --period 24h).
environment: default prod (pass as part of --query, e.g., environment:production).
limit: default 20 (pass as --limit).
search_query: optional --query parameter, uses Sentry search syntax (e.g., is:unresolved, assigned:me).
issue_short_id: use directly with sentry issue view.

Output formatting rules

Issue list: show title, short_id, status, first_seen, last_seen, count, environments, top_tags; order by most recent.
Event detail: include culprit, timestamp, environment, release, url.
If no results, state explicitly.
Redact PII in output (emails, IPs). Do not print raw stack traces.
Never echo auth tokens.

Golden test inputs

Org: {your-org}
Project: {your-project}
Issue short ID: {ABC-123}

Example prompt: "List the top 10 open issues for prod in the last 24h." Expected: ordered list with titles, short IDs, counts, last seen.

OpenAIGet→

Query and analyze Sensors Analytics user behavior data with natural language.

—Get→

$ loading_