Waxell

skill

dd-coreweave-agent-fleet-installation-on-clusters High risk

datadog-labsdatadog-labs/agent-skillsupdated

Install the Datadog Agent on the CoreWeave Kubernetes (CKS) clusters of a tenancy that is already connected to Datadog, so container monitoring and APM telemetry flow into Datadog without connecting to each cluster or running Helm yourself. Discovers the tenant's integrated account and its CKS clusters, asks which clusters to cover, and creates the Datadog install rule that makes Datadog install and manage the Agent fleet. Datadog rolls the Operator out from there; the skill stops at rule creation. The feature is in preview. Use when the user wants Datadog monitoring on their CoreWeave…
datadog-labs's own description, from the skill's files.
Stars
185
Version
v1
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 19 findings, highest severity critical.

Highest severity
critical
Findings
19
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 today

Result

High risk Waxell rates it high risk: 19 findings, highest severity critical.

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 (19)

critical · 1

  • critical

    Data Flow: Tainted flow: 'request' from os.environ.get (line 299, credential/environment) → urllib.request.urlopen (netw

    scripts/_datadog.py:303 · skillspector:TT3

high · 10

  • high

    Privilege Escalation: Credential Access

    SKILL.md:101 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/_coreweave.py:256 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/_coreweave.py:454 · skillspector:PE3

  • high

    System Prompt Leakage: Direct Prompt Extraction

    scripts/_datadog.py:925 · skillspector:P6

  • high

    System Prompt Leakage: Direct Prompt Extraction

    scripts/setup.py:561 · skillspector:P6

  • high

    System Prompt Leakage: Direct Prompt Extraction

    scripts/_datadog.py:976 · skillspector:P6

  • high

    Privilege Escalation: Credential Access

    scripts/dd-env.sh:4 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/dd-env.sh:10 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/dd-env.sh:4 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/dd-env.sh:7 · skillspector:PE3

medium · 8

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:64 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:186 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:194 · skillspector:EA2

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/_coreweave.py:22 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/_datadog.py:142 · skillspector:AST4

  • medium

    Data Flow: Tainted flow: 'command' from os.environ.get (line 528, credential/environment) → subprocess.run (code executi

    scripts/_datadog.py:142 · skillspector:TT2

  • medium

    Dangerous Code Execution: subprocess module call

    scripts/_datadog.py:218 · skillspector:AST4

Versions

Version history

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

One version so far: v1 (0.1.0), seen 2026-11-21.

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