Security audit

API Test Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent API test automation helper that writes local test/report files and may run user-directed API tests, with no evidence of hidden payloads, persistence, or exfiltration.

Install only if you want an agent to generate and possibly run API tests. Use non-production targets by default, review generated requests before execution, and provide credentials through environment variables or a managed secret flow rather than hard-coding them in generated files.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The code chunk’s primary purpose is narrow: assembling a test report from pre-existing manifest and execution result JSON files. While report generation is one part of the declared description, the description claims a much broader end-to-end capability centered on test-case generation and execution from API documentation. None of those core capabilities appear in this code. There are no unrelated dangerous behaviors or inconsistent resource accesses; the mismatch is that the actual behavior is only a reporting subcomponent, not the described complete automated API testing workflow.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The declared description promises an end-to-end API test automation capability: ingesting API documentation, generating complete executable tests, configuring scripts/environment, running the suite, and reporting outcomes. The supplied code only prepares a filesystem workspace skeleton with empty directories and template files. While the generated files include placeholders for environment config and shared scripts, they are not populated from interface docs and no tests are created or run. This is therefore a material description-behavior mismatch: the implementation is merely setup/scaffolding, not full automated API test generation and execution.
Content: No source excerpt is available for this finding.

Hidden Instructions

High

Category: Prompt Injection
Confidence: 60% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Content: Scanner excerpt · assets/templates/test-plan.template.md (reported line 1)May include surrounding context.
md
# Report Contract Use this reference when building the final output after generating or executing API automated tests.

Hidden Instructions

High

Category: Prompt Injection
Confidence: 60% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Content: Scanner excerpt · references/environment-contract.md (reported line 1)May include surrounding context.
md
# Report Contract Use this reference when building the final output after generating or executing API automated tests.

Hidden Instructions

High

Category: Prompt Injection
Confidence: 60% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Content: Scanner excerpt · references/report-contract.md (reported line 1)May include surrounding context.
md
# Report Contract Use this reference when building the final output after generating or executing API automated tests.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 84% confidence
Finding: The skill clearly instructs reading reference files and generating workspace files, but it does not declare an explicit tool scope such as allowed-tools or permissions. In an agent environment, missing scope boundaries can let the skill exercise broader file read/write capabilities than reviewers or users expect, increasing the chance of unintended file access or modification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill directs execution of generated API tests, setup hooks, and environment-variable injection without an explicit warning about side effects on live systems, accounts, or data. In this context, generated tests may create, update, or delete remote resources, consume production credentials, or trigger destructive setup/teardown flows if run against the wrong environment.
Content: No source excerpt is available for this finding.

Ae2

Medium

Category: analysis-evasion
Confidence: 90% confidence
Finding: Artifact content does not match its filename extension
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This code creates parent directories and writes both markdown and JSON output files based on command-line arguments, which is a file-modifying operation. Although expected for a report builder, the file itself provides no inline comment, docstring, or user-facing disclosure near the write operations describing that it will create directories and overwrite report files.
Content: No source excerpt is available for this finding.