Back to skill

Security audit

Dependency Audit

Security checks for vulnerabilities and agentic risk

Overview

This dependency-audit skill is coherent and purpose-aligned, but users should approve any installs or dependency changes before they are run.

Install only if you want an agent to run dependency audits in project directories. Treat audit commands as mostly read-only, but require explicit confirmation before `pip install`, `cargo install`, `npx`, `npm audit fix`, `npm update`, `npm install`, `npm uninstall`, or package upgrades; run them in a clean branch or isolated environment when possible.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:44
Finding

Unpinned Third-Party Audit Tools Are Installed and Executed

Content
View full analysis
/dev/null ``` ### Technical Analysis The Skill instructs the Agent to install or execute third-party packages without pinning reviewed versions, verifying integrity hashes, validating publishers, or obtaining explicit user approval. In particular, `npx depcheck` may retrieve the current registry version and immediately execute package-controlled code. The `pip install` and `cargo install` commands similarly rely on mutable registry content and may execute package or build-system behavior during installation. The effective code executed by the Skill can therefore change after the Skill itself has been reviewed. This creates a supply-chain risk if a named package, publisher account, registry, or transitive dependency is compromised. It also increases exposure to dependency-confusion and package-substitution attacks when untrusted registry configuration is present. ### Attack Path 1. An attacker compromises one of the named packages, its publisher account, or a transitive dependency. 2. Alternatively, the execution environment is configured to use a malicious or untrusted package registry. 3. The requested audit utility is not already installed. 4. The Skill runs an unversioned `pip install`, `cargo install`, or `npx` command. 5. The package manager downloads the current, unverified package contents. 6. Package-controlled installation, build, or runtime code executes with the Agent process's permissions. 7. The malicious code can access resources available to that process, including project files, environ ...[truncated 749 chars]
Remediation
View remediation
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase security audit is broad and likely to match user requests unrelated to dependency scanning, causing this skill to activate in contexts it was not intended for. Misactivation can lead the agent to propose or run ecosystem-specific audit and install commands in the wrong project or against an overly broad request, increasing the chance of unsafe or unintended changes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger outdated packages is ambiguous and can refer to OS packages, containers, language runtimes, or application dependencies. In an agent setting, that ambiguity can invoke this skill outside its intended scope and produce irrelevant or potentially environment-modifying commands.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill recommends installing audit tools and later suggests update commands such as npm audit fix, npm update, and package upgrades without an explicit warning that these actions can modify the environment, dependency graph, and lockfiles. In automated or semi-automated agent use, this can lead to unreviewed code execution from registries and unintended project changes during what users may expect to be a read-only audit.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs use of npx depcheck without pinning a specific version, which causes execution of whatever version is currently resolved from the registry at runtime. That creates a supply-chain risk: a compromised, typosquatted, or newly malicious release could be fetched and executed in the user's environment during an audit workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.