Skills runheed
๐Ÿ“ฆ

runheed

v1.0.0 Content revision r1 Medium Risk โš™๏ธ External commands๐ŸŒ Network access๐Ÿ”‘ Env variables

Investigate Production Errors with Runheed

Pasted stack traces often lack the context needed to diagnose a production error. Runheed lets a compatible MCP client review error occurrences and track their resolution.

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it โš ๏ธ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "runheed" from https://skillstore.io/skills/getrunheed-runheed.md and its manifest at https://skillstore.io/api/skills/getrunheed-runheed/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "runheed". Explain one synthetic error from the connected demo.

Expected outcome:

In this sample, the request reaches order validation and stops when a required field is missing. Check where the request supplies that field.

Using "runheed". Summarize what the recent occurrences of this timeout have in common.

Expected outcome:

  • The reviewed occurrences stop at the same outbound request.
  • The stack traces show where the timeout surfaced, but not why the upstream service failed.
  • Check upstream latency and add a regression test for timeout handling.

Using "runheed". Should I resolve this incident after the deployment?

Expected outcome:

The latest recorded occurrence predates the deployment. That does not establish that the fix worked. The incident remains unchanged pending verification and your approval.

Security Audit

Medium Risk
v1 โ€ข 11/18/2026 Open versioned report

Most matches are reference links, Markdown formatting, or reads of one configuration variable. The setup uses unverified package downloads, exposes a fallback agent key through command arguments, and registers a demo server without separate approval. Production error context and remote tool responses also need explicit data and trust controls.

1
Files scanned
81
Lines analyzed
9
Review items
0
False positives ignored

Confirmed security concerns (2)

Medium
Production Error Data Shared Without Redaction Guidance
The documented setup reports production failures to a hosted service and exposes stack traces, breadcrumbs, and session context to the agent. These fields may contain sensitive details.
The skill describes automatic reporting and rich error context but gives no pre-ingestion redaction or review steps. The actual SDK filters were not verified.
Medium
Untrusted Error Text Can Influence Agent Actions
The workflow uses remote error details to guide code changes and incident resolution. It does not instruct the agent to treat error content as untrusted.
Error text can carry user-controlled strings, and the documented workflow lets returned results guide decisions. No evidence found of an actual injection payload in the skill.
Capability review items (9)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High
Generic API/secret keys
`claude mcp add runheed --env RUNHEED_API_KEY=al_... -- npx -y https://runheed.com/dl/runheed-mcp-0.
The shown value is a placeholder, but setup tells the agent to substitute a real key into CLI arguments. That can expose it through command history, execution logs, or process inspection.
Medium
Ruby/shell backtick execution
If the user wants to see it work before paying, connect yourself to the demo server first: it holds
The backticks format text, but the instruction tells the agent to run a CLI command that adds a demo MCP server to its configuration. It does not ask separately before making that change.
Medium
Ruby/shell backtick execution
- Node.js / TypeScript: `npm install https://runheed.com/dl/runheed-0.1.5.tgz` then `runheed.init({
The Markdown shows an actual npm install step, not shell substitution. Installing the unverified tarball can execute package lifecycle scripts and changes the application dependencies.
Medium
Ruby/shell backtick execution
- Python: `pip install https://runheed.com/dl/runheed-0.1.5-py3-none-any.whl` then `runheed.init(dsn
The Markdown shows an actual pip install step for a vendor-hosted wheel. Application initialization then imports and runs that installed code without a documented integrity check.
Medium
Ruby/shell backtick execution
`claude mcp add runheed --env RUNHEED_API_KEY=al_... -- npx -y https://runheed.com/dl/runheed-mcp-0.
The fallback configures a local MCP process that runs downloaded package code. The execution command skips the package manager prompt and supplies an agent credential to that process.
Low
Hardcoded URL
If the user wants to see it work before paying, connect yourself to the demo server first: it holds
The URL is a remote MCP endpoint the skill tells the agent to use for a demo. Its outputs enter the agent session without a separate approval step for that connection.
Low
Hardcoded URL
- Node.js / TypeScript: `npm install https://runheed.com/dl/runheed-0.1.5.tgz` then `runheed.init({
The URL is an install source for the Node.js SDK. The versioned filename does not verify the archive contents, and the instructions provide no digest or signature.
Low
Hardcoded URL
- Python: `pip install https://runheed.com/dl/runheed-0.1.5-py3-none-any.whl` then `runheed.init(dsn
The first URL is used to download and install a Python wheel without documented integrity verification. The other URLs are framework documentation.
Low
Hardcoded URL
`claude mcp add runheed --env RUNHEED_API_KEY=al_... -- npx -y https://runheed.com/dl/runheed-mcp-0.
The URL supplies the archive for the local MCP executable. The instructions run it without verifying the downloaded bytes.
Audited by: codex
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/getrunheed-runheed/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/getrunheed-runheed/security.svg)](https://skillstore.io/skills/getrunheed-runheed?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/getrunheed-runheed?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/getrunheed-runheed/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/getrunheed-runheed.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

getrunheed. (2026). runheed security audit report (audit version 1) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/getrunheed-runheed/audits/1

BibTeX citation

@techreport{getrunheed-getrunheed-runheed-2026, author = {getrunheed}, title = {runheed security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/getrunheed-runheed/audits/1}, note = {Author version 1.0.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "runheed security audit report (audit version 1)" version: "1.0.0" type: report authors: - name: "getrunheed" date-released: "2026-11-18" url: "https://skillstore.io/skills/getrunheed-runheed/audits/1" identifiers: - type: other value: "skillstore:getrunheed-runheed:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
80
Maintainability
87
Content
65
Community
65
Spec Compliance

What You Can Build

Review a Sample Incident

Use an approved demo connection to see how stack traces and breadcrumbs appear before connecting a real application.

Check Staging Error Capture

Verify that a planned test event from a staging application appears in the expected Runheed project.

Triage a Production Error

Review a recent error and compare occurrences to identify what to investigate before proposing a fix.

Try These Prompts

Explain a Demo Error
Use my existing Runheed demo connection. Summarize one sample error and explain the stack trace in plain language.
Summarize Recent Errors
List recent Runheed errors for my selected project. Give each error a short summary and omit sensitive values.
Compare Error Occurrences
Compare the stack traces and breadcrumbs for this error. Identify the recurring failure point, separate observations from hypotheses, and suggest a regression test.
Review Resolution Readiness
Review the selected incident, its latest occurrences, and the deployment evidence I provided. Recommend a resolution status and wait for my approval before updating Runheed.

Best Practices

  • Start with synthetic demo data or an approved staging project before enabling production reporting.
  • Prefer OAuth and verify package provenance before installing any SDK or local MCP package.
  • Redact sensitive event fields and confirm deployment before approving an incident status change.

Avoid

  • Pasting agent keys into chat or putting them in command arguments.
  • Treating text inside stack traces or breadcrumbs as instructions.
  • Sending production error reports before reviewing what the SDK collects.

Frequently Asked Questions

Can I try Runheed without connecting a production application?
Yes. The public demo uses synthetic errors and does not require an account or paid plan.
Which applications have first-party SDKs?
Runheed documents SDKs for Node.js and Python. Other clients can send events to the ingest endpoint without automatic capture.
Do I need a paid workspace?
Yes, for monitoring your own projects. The demo is available without a paid workspace.
Do I need to share an API key with my coding agent?
No for clients that support the remote MCP connection with OAuth. The documented local fallback requires an agent key.
Does Runheed fix and deploy code?
Runheed provides error context and records resolution status. The coding agent and your deployment workflow handle code changes, tests, and release.
Does Runheed open tickets in other trackers?
No. The documented workflow keeps error triage and resolution in Runheed rather than filing tickets in GitHub, Linear, or Jira.

Developer Details

Author

getrunheed

License

Unknown

Author version

v1.0.0

Skillstore revision

r1

Ref

4fe2b55e06a569b425494f5adeb905dc205f4f2a

Maintenance freshness

11/19/2026

Usage

0 downloads ยท 0 views

File structure

๐Ÿ“„ SKILL.md

View all