Security audit

Jarvis Test Gap Finder 01

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown planning skill with an overbroad test-gap label, but it does not request sensitive access, install code, persist, or perform unsafe actions.

Before installing, treat this as a generic planning checklist rather than a specialized test-gap finder. It appears safe from a security standpoint, but users expecting failure-mode and business-impact test analysis may want the publisher to narrow the description and add concrete test coverage steps.

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

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The manifest and title present this as a specialized test-gap-finding skill, but the body implements a generic planning workflow with no concrete method for identifying missing tests by failure mode or business impact. This mismatch can cause inappropriate routing or invocation, leading users or higher-level agents to apply the skill in contexts where they expect focused QA/test analysis but instead receive broad development guidance.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The description is broad enough to match many ordinary development-assistance requests, which increases the chance that the skill is invoked outside its supposed specialty. Over-broad activation language is dangerous in agent systems because it can shadow more appropriate skills and produce irrelevant or misleading outputs under a trusted, specialized label.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The core summary, 'Deliver a concrete, reusable workflow for development tasks,' is generic and lacks boundaries that would constrain when the skill should activate. In a multi-skill environment, such ambiguity can cause misrouting and untrusted substitution of a generic process skill for a domain-specific testing skill, reducing reliability and potentially bypassing intended safeguards.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The example prompts are broad, everyday development requests that do not mention missing tests, failure modes, or business impact, effectively training users and orchestrators to invoke the skill for general planning tasks. This expands the skill's operational scope beyond its declared function and makes misapplication more likely, especially because examples strongly influence tool-selection behavior.

Static analysis

No suspicious patterns detected.