Security audit

Jenkins Skills

Security checks across malware telemetry and agentic risk

Overview

This Jenkins skill is purpose-built and not deceptive, but it can implicitly run or disable CI jobs using Jenkins credentials without a clear confirmation gate.

Install only if you trust the publisher and will use a least-privilege Jenkins API token. Prefer a token limited to specific non-production jobs, require human confirmation before build/enable/disable actions, protect ~/.devops-skills/jenkins.json with restrictive permissions, and update the requests dependency floor before use in sensitive environments.

SkillSpector

By NVIDIA

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill clearly relies on environment-sourced credentials and network access to a Jenkins server, yet no permissions are declared in the manifest. That mismatch weakens review and user awareness, making it easier for a skill with privileged CI access to be invoked without clear disclosure of its sensitive capabilities.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The description and trigger guidance are broad enough to catch general DevOps or engineering-efficiency requests, which can cause the skill to activate in situations where the user did not specifically ask to operate Jenkins. Because this skill can trigger builds and change job state, overbroad routing increases the chance of unintended high-impact actions.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The documentation advertises build triggering and job enable/disable functionality without prominently warning that these are state-changing operations that may launch deployments, consume infrastructure, or interrupt CI/CD workflows. In a Jenkins context, unintended execution can have direct operational and production impact, so the missing warning materially increases risk.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The manual advertises very broad natural-language trigger phrases such as running a job, checking recent build status, and showing logs, without defining strict invocation boundaries or confirmation requirements. In an agentic environment, this can cause accidental invocation from ordinary conversation, leading to unintended Jenkins actions including build execution, job enable/disable operations, or exposure of build logs.

Known Vulnerable Dependency: requests==2.25 — 8 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High

Category: Supply Chain
Confidence: 96% confidence
Finding: requests==2.25

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.