Waxell

skill

dd-coding-agent-mcp Review findings

datadog-labsdatadog-labs/agent-skillsupdated

Connect the coding agent you are running in (Claude Code, Codex, Gemini CLI, OpenCode, Cursor, or GitHub Copilot CLI) to the Datadog MCP server with the right toolsets, then confirm the tools are there. Takes the toolsets to turn on from the calling skill or the user; with none given it turns on everything generally available, and falls back to the core toolset if that fails. Use when the user wants Datadog tools in their coding agent, when another skill needs Datadog MCP tools that aren't in your tool list, or when the Datadog MCP server is connected but missing tools. Not for building MCP…
datadog-labs's own description, from the skill's files.
Stars
185
Version
v1
Copies
0

Overview

holdReview findings

Waxell's checks found 4 findings to review, highest severity high.

Highest severity
high
Findings
4
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

Review findings Waxell's checks found 4 findings to review, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (4)

high · 3

  • high

    Agent Snooping: Agent Config Directory Access

    references/clients.md:25 · skillspector:AS1

  • high

    Agent Snooping: Agent Config Directory Access

    references/clients.md:26 · skillspector:AS1

  • high

    Agent Snooping: Agent Config Directory Access

    references/clients.md:40 · skillspector:AS1

medium · 1

  • medium

    Data Exfiltration: External Transmission

    SKILL.md:64 · skillspector:E1

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

One version so far: v1 (0.2.0), seen 2026-11-20.

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all