Security audit

Software Data Admapix Raw Developer Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only helper skill with overly broad activation wording, but it does not include executable code, persistence, credential handling, or destructive behavior.

Before installing, be aware that this skill may activate on ordinary software or data requests because its trigger terms are broad. It appears safe from a security standpoint, but maintainers should narrow the triggers to AdMapix-specific requests to avoid confusing routing.

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description defines activation using very broad terms like 'software-and-data', 'raw', 'data', 'layer', and generic needs such as any 'workflow, artifact, checklist, analysis, or implementation support'. This can cause the skill to be invoked for many unrelated requests, creating prompt-scope confusion and increasing the chance that users receive irrelevant or unintended instructions under this skill's authority.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes highly generic terms such as 'raw', 'data', 'layer', 'apps', 'rankings', 'revenue', and 'bug fix', which are common across normal technical conversations. Such vague triggers significantly raise the risk of accidental invocation, misrouting, and overbroad skill application to unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keyword set is overly broad, including generic terms like "raw", "data", "layer", and "apps" that can appear in many unrelated requests. This can cause unintended skill activation, routing users into the wrong workflow and potentially exposing them to irrelevant or unsafe guidance in contexts where this skill was not intended to run.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence uses a highly generic help-request pattern that can match ordinary user language rather than a narrowly scoped invocation. This can cause unintended activation of the skill in unrelated conversations, leading to context hijacking, incorrect routing, or accidental exposure of the skill's capabilities when another tool should have been selected.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are broad, repetitive, and partially truncated, making it plausible that unrelated user requests could accidentally invoke this skill. Unintended invocation is risky because this skill appears designed to shape workflows and implementation guidance, so accidental activation could cause irrelevant or unsafe actions to be taken in the wrong context.
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, generic, and partially composed of ordinary help-request language, which can cause the skill to activate outside its intended scope. In an agent ecosystem, unintended activation can route unrelated user requests into this skill, causing misexecution, confused delegation, and potentially unsafe handling of tasks the skill was not meant to perform.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences are truncated and malformed, and they do not provide clear or testable activation boundaries. This ambiguity makes it harder for maintainers and routing logic to distinguish valid use from accidental matches, reducing reliability and increasing the chance of unintended activation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The invocation guidance embeds a long demand statement directly into the description without clearly separating eligibility criteria from background context. This ambiguity can cause overmatching or inconsistent activation behavior, making it easier for the skill to be invoked outside its intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger phrases use broad, natural-language patterns such as "Help me" and "I need a practical workflow," which are common in benign user requests across many domains. If used as activation exemplars, they can train or encourage routing systems to invoke this skill too broadly, increasing accidental activation and response confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt uses a very broad natural-language trigger phrase and combines multiple generic terms, which can cause the skill to activate in situations beyond its intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt collisions, or untrusted context being handled by this skill when another tool would be more appropriate.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This trigger pattern is ambiguous because it follows a common request template ('I need a practical workflow for...') without requiring sufficiently specific domain terms. In a routing system, ambiguous triggers increase the chance that unrelated tasks are captured by this skill, which can degrade reliability and create unsafe or unauthorized workflow execution paths.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This file is labeled as a Chinese README, but key descriptive and usage content is presented in English, which can effectively impose a language choice on users expecting a Chinese-localized document. There is no note explaining the bilingual behavior or offering the user a language preference.
Content: No source excerpt is available for this finding.