Back to skill

Security audit

API Integration for RedHat MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API-integration guidance skill; the scanner’s remote-script warning is a false positive from text that tells users to avoid that pattern.

Before installing, note that this skill may guide an agent to write code that calls authenticated third-party APIs, so review generated clients for correct secret sourcing, timeouts, retry bounds, and logging. The publisher should fix the malformed trigger metadata, but the artifact itself is coherent and non-executable.

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
  • 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 (3)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
## Safety Rules
- Do not paste tokens/keys into code or logs.
- Do not rely on “best effort” network calls without timeouts.
- Avoid `curl | sh` or ad-hoc install scripts as part of integration.

## Example
Integrate “VendorAPI”:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · api-integration.md (reported line 43)May include surrounding context.

md
## Safety Rules
- Do not paste tokens/keys into code or logs.
- Do not rely on “best effort” network calls without timeouts.
- Avoid `curl | sh` or ad-hoc install scripts as part of integration.

## Example
Integrate “VendorAPI”:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger field is effectively malformed or unspecified (System.Object[]), which makes the skill's activation conditions unclear and potentially subject to unintended matching or loader-dependent behavior. In an API integration skill that can perform authenticated outbound actions, ambiguous triggering increases the risk of accidental invocation, misuse by other components, or inconsistent enforcement of safety boundaries.

Content

No source excerpt is available for this finding.