Waxell

skill

agent-observability-eval-pipeline High risk

datadog-labsdatadog-labs/agent-skillsupdated

End-to-end Agent Observability pipeline for an instrumented ml_app, classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-bootstrap`, `agent-observability-experiment-analyzer`). Use when user…
datadog-labs's own description, from the skill's files.
Stars
185
Version
v1
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 17 findings, highest severity high.

Highest severity
high
Findings
17
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: 17 findings, 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 (17)

high · 12

  • high

    Privilege Escalation: Credential Access

    SKILL.md:155 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:14 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:15 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/publish_dataset.py:71 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/publish_dataset.py:81 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:14 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:15 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:37 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:39 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:44 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:38 · skillspector:PE3

  • high

    Privilege Escalation: Credential Access

    scripts/load_env.py:40 · skillspector:PE3

medium · 5

  • medium

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

    SKILL.md:1 · skillspector:LP3

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:112 · skillspector:RA2

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:354 · skillspector:EA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:381 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:381 · skillspector:RA2

Versions

Version history

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

One version so far: v1, 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 data & analytics skills and plugins

See all