Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only unit-test helper, with the main caveat that its broad trigger wording may cause it to activate more often than intended.

Install only if you want a broadly available helper for unit-test and coverage workflows. Be aware it may be auto-selected for general testing or quality requests, so explicit skill invocation or narrower trigger settings would improve routing precision.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is extremely broad and can match ordinary user phrasing, causing the skill to activate in situations where the user did not explicitly intend to invoke a unit-test-coverage workflow. Over-broad activation is dangerous because it can route unrelated requests into this skill, creating prompt hijacking opportunities, incorrect tool behavior, or disclosure of context to an unnecessary skill path.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is so generic that it can match ordinary user requests and cause the skill to activate unintentionally. In an agent system, overly broad activation increases prompt-routing risk, where the wrong skill handles a request and may produce irrelevant or unsafe actions outside the user's intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger lacks clear boundaries and can be interpreted as a catch-all request for a 'practical workflow,' which overlaps with many normal software-assistance prompts. That ambiguity makes accidental invocation more likely and reduces routing precision, which can indirectly affect security by sending sensitive development tasks to an inappropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad enough to match ordinary requests about testing, unit tests, coverage, or regression, which can cause the skill to activate outside narrowly intended scenarios. Overbroad activation increases the chance of inappropriate routing, prompt interference with other skills, and unnecessary exposure of users' code or context to a workflow they did not explicitly request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are broad and generic enough to match many normal software-assistance requests, which increases the chance that this skill is invoked when the user did not specifically intend to use it. Over-broad activation can cause skill routing collisions, unexpected prompt injection surface expansion, or misapplication of testing-oriented guidance in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences use highly generic phrasing like 'Help me' and 'I need a practical workflow,' which can train or encourage activation on routine requests rather than deliberate skill selection. This makes the skill easier to trigger accidentally and increases the risk of incorrect routing, especially in environments with many overlapping software-support skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keywords include broad, generic terms such as "testing" and "quality" that commonly appear in unrelated user requests. This can cause the skill to activate outside its intended scope, leading to inappropriate routing, irrelevant guidance, or overshadowing of a more suitable skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are written in very broad natural language that overlaps with ordinary conversation, which increases the chance of accidental invocation. In an agent environment, this can degrade reliability by causing the wrong skill to engage and potentially expose internal workflow behavior unnecessarily.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt uses a very broad trigger phrase covering general software, testing, regression, workflow, artifact, checklist, analysis, and implementation support. This can cause the skill to be invoked in contexts far beyond the user's specific intent, increasing the chance of inappropriate routing, prompt interference, or accidental exposure of repository-specific testing tasks to the wrong skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Enabling implicit invocation without clear constraints allows the platform to auto-select this skill for loosely related requests. In a broad engineering environment, that can lead to unintended activation on unrelated coding tasks, increasing the attack surface for prompt confusion, mis-scoped actions, or unauthorized handling of codebase-specific testing requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation guidance provides only positive trigger examples and lacks specificity about exclusions, making accidental or adversarial activation more likely. In agent systems, ambiguous routing increases the chance that unrelated prompts get handled by this skill, which can degrade security boundaries and produce inappropriate actions or misleading outputs.
Content: No source excerpt is available for this finding.