Entry point for Datadog onboarding. Takes a developer's plain-language goal, ensures a valid Datadog account with dd-account-setup, asks dd-product-recommender which products fit, detects the project's platform and cloud, then composes an ordered plan across the existing skills (agent install, product enable, verify, and optional cloud integration) and dispatches to each by source URL, honestly flagging products with no skill yet. Use when the user says "set up Datadog", "onboard my app / this repo to Datadog", "instrument my project", or states a monitoring goal without naming a specific…
- Stars
- 185
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 34 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 34
- 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
High risk Waxell rates it high risk: 34 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 (34)
critical · 1
- critical
Data Flow: Tainted flow: 'request' from os.environ.get (line 347, credential/environment) → urllib.request.urlopen (netw
scripts/emit.py:349 · skillspector:TT3
high · 10
- high
Rogue Agent: Self-Modification
SKILL.md:48 · skillspector:RA1
- high
Rogue Agent: Self-Modification
scripts/resolve.py:827 · skillspector:RA1
- high
Tool Misuse: Chaining Abuse
SKILL.md:169 · skillspector:TM2
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:335 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:375 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:388 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:392 · skillspector:AE1
- high
Privilege Escalation: Credential Access
scripts/emit.py:295 · skillspector:PE3
- high
Privilege Escalation: Credential Access
scripts/emit.py:295 · skillspector:PE3
- high
Privilege Escalation: Credential Access
scripts/emit.py:721 · skillspector:PE3
medium · 23
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Data Exfiltration: External Transmission
catalog.json:49 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:87 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:269 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:307 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:350 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:393 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:562 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:744 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:1678 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:1766 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:1854 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:1942 · skillspector:E1
- medium
Data Exfiltration: External Transmission
catalog.json:2030 · skillspector:E1
- medium
Data Flow: Tainted flow: '_debug_log_path()' from os.environ.get (line 144, credential/environment) → open (file write)
scripts/emit.py:153 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'marker' from os.environ.get (line 276, credential/environment) → open (file write)
scripts/emit.py:278 · skillspector:TT2
- medium
Data Flow: Tainted flow: '_run_dir()' from os.environ.get (line 391, credential/environment) → open (file write)
scripts/emit.py:364 · skillspector:TT2
- medium
Data Flow: Tainted flow: '_current_session_path()' from os.environ.get (line 407, credential/environment) → open (file w
scripts/emit.py:430 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'temporary' from os.environ.get (line 466, credential/environment) → open (file write)
scripts/emit.py:467 · skillspector:TT2
- medium
Data Flow: Tainted flow: '_ndjson_path()' from os.environ.get (line 549, credential/environment) → open (file write)
scripts/emit.py:559 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'path' from os.environ.get (line 727, credential/environment) → open (file write)
scripts/emit.py:739 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'temporary' from os.environ.get (line 896, credential/environment) → open (file write)
scripts/emit.py:897 · skillspector:TT2
- medium
Data Exfiltration: External Transmission
scripts/fetch_skill.py:72 · 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 (2), seen 2026-11-16.
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 productivity skills and plugins
dd-slack-integrationdatadog-labsConnects a commercial Slack workspace to Datadog and adds a channel to it, so the user can receive Datadog alerts and notifications in… High riskProductivityDesign185
prisma-upgrade-v7prismaComplete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7… Review findingsProductivity80
huawei-cloud-cloudrobo-dispatchhuaweicloudManage CloudRobo embodied-agent task dispatch (robo-dispatcher), create embodied tasks that drive a robot via an exec/model and… High riskProductivityAI & agents59
huawei-cloud-cloudrobo-model-adapt-workflowhuaweicloudOne-stop workflow for adapting models on the CloudRobo platform. Chains 4 sub-skills: huawei-cloud-cloudrobo-npu-patcher (PyTorch VLA →… High riskProductivityData & analytics59