online-evals

Name: agent-skills/online-evals
Author: launchdarkly

Share on X Share on LinkedIn Share on Bluesky

15Low

The skill performs unauthorized network communication and executes arbitrary commands without declaring necessary tool permissions, creating a significant risk of data exfiltration and unconstrained system access.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 7/3/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction3 findings

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

HygienePackaging & Manifest1 finding

Skill Info

Namelaunchdarkly/agent-skills/online-evals

Registrygithub

Version913b74564ca4

PURLpkg:github/launchdarkly/agent-skills@913b74564ca4?skill=online-evals

Stars19

Installs959

Source

Repository ↗SKILL.md ↗

Install

GitHub

959 installs

Skills.shDocs

npx skills add https://github.com/launchdarkly/agent-skills

Assessments (3)

AI Agent Traps ↗

Missing allowed-tools declarationlowunauthorized tool useAML.T0053LLM06:2025

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Undeclared network usagelowunauthorized tool useAML.T0053LLM06:2025

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence

Outbound network request primitive in skill code — can transmit data externallylowdata exfiltrationAML.T0025AML.T0024LLM02:2025

Outbound network request primitive in skill code — can transmit data externally (seen 3 times in this file at lines 55, 69, 93)

95% confidenceline 55

requests.post(config_url, headers=self.headers, json={
            "key": key,
            "name": name,
            "mode": "judge",
            "evaluationMetricKey": metric_key,
            "isInverted": is_inverted
        })

Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/launchdarkly/agent-skills/online-evals.svg)](https://mondoo.com/ai-agent-security/skills/github/launchdarkly/agent-skills/online-evals)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/launchdarkly/agent-skills/online-evals"><img src="https://mondoo.com/ai-agent-security/api/badge/github/launchdarkly/agent-skills/online-evals.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/launchdarkly/agent-skills/online-evals.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow