Connect a CoreWeave namespace to Datadog so its metrics and logs are collected through the Datadog CoreWeave Cloud integration. Guides creating the CoreWeave access token the integration needs, the token is entered in a separate secure prompt and never shown to the agent, and registers the integration and checks that its data arrives. Use when the user wants to connect CoreWeave to Datadog, collect CoreWeave metrics or logs, or configure the Datadog CoreWeave integration. Not for changing an existing CoreWeave account.
- Stars
- 185
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 26 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 26
- 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: 26 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 (26)
critical · 2
- critical
Tells Claude to download a script and pipe it to a shell
SKILL.md:42 · skill_risk:S1
- critical
Tells Claude to download a script and pipe it to a shell
SKILL.md:58 · skill_risk:S1
high · 7
- high
Privilege Escalation: Credential Access
SKILL.md:3 · skillspector:PE3
- high
Privilege Escalation: Credential Access
SKILL.md:87 · skillspector:PE3
- high
Privilege Escalation: Credential Access
SKILL.md:89 · skillspector:PE3
- high
Supply Chain: External Script Fetching
SKILL.md:58 · skillspector:SC2
- high
Tool Misuse: Chaining Abuse
SKILL.md:64 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
SKILL.md:67 · skillspector:TM2
- high
Tells Claude to install unpinned packages (@datadog/pup)
SKILL.md:43 · skill_risk:S2
medium · 15
- 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:45 · skillspector:EA2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md:68 · skillspector:PE2
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md:142 · skillspector:EA2
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:120 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:219 · skillspector:AST4
- medium
Privilege Escalation: Sudo/Root Execution
scripts/setup.py:275 · skillspector:PE2
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:414 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:436 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:466 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:475 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:509 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/setup.py:821 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/verify_data.py:60 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/verify_data.py:116 · skillspector:AST4
low · 2
- low
Supply Chain: External Script Fetching
SKILL.md:42 · skillspector:SC2
- low
Supply Chain: External Script Fetching
SKILL.md:64 · skillspector:SC2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1 (1.0.0), 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 data & analytics skills and plugins
dd-dbm-rds-postgresdatadog-labsSet up Datadog Database Monitoring (DBM) for a standalone PostgreSQL instance on AWS RDS (not Aurora) - enable pg_stat_statements on the… High riskData & analyticsEngineering185
dd-gcp-ccmdatadog-labsSet up Datadog Cloud Cost Management for GCP - enables the BigQuery and BigQuery Data Transfer APIs, walks the user through the Cloud… High riskData & analyticsEngineering185
dd-instrument-product-analyticsdatadog-labsSwitches on Datadog Product Analytics (funnels, retention, pathways, user journeys) for a browser app that runs the Datadog RUM Browser… Review findingsData & analyticsEngineering185
dd-logsdatadog-labsDatadog Log Management. Search and analyze logs in Datadog, configure archives, log-based metrics, and exclusion filters, and control… Review findingsData & analyticsEngineering185