Back to skill

Security audit

Compose

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local reference script that prints documentation and does not access files, credentials, networks, or persistent system settings.

Installers should treat this as a low-risk reference skill, but should expect generic documentation rather than authoritative, product-specific Compose guidance. It does not appear to need credentials or network access.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/script.sh (reported line 64)May include surrounding context.

sh
## Prerequisites
- Basic understanding of data concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says this skill is a reference tool for Compose concepts, best practices, and implementation patterns. However, the script emits broad placeholder documentation about a generic 'compose' tool in 'data contexts' rather than actual Compose-specific reference content, so the implemented behavior does not match the claimed subject matter.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file header says 'compose — Compose reference tool. Use when working with compose in data contexts,' which frames the tool as data-domain guidance. That directly conflicts with the manifest description that positions the skill as a devtools reference covering Compose concepts and implementation patterns.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file describes the skill in broad terms such as 'covers intro, quickstart, patterns and more' and 'Quick lookup for Compose concepts' without stating when the skill should or should not be invoked. The command list exists, but there are no explicit trigger constraints or negative examples to reduce unintended activation from general Compose-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.