Security audit

Software Data Admapix Raw Developer Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only helper with overly broad activation wording, but it does not add executable, persistent, credential-seeking, or destructive behavior.

Before installing, be aware this skill may activate for broad software or data requests because of its generic trigger words. It appears safe as a documentation-only helper, but users should verify any suggested commands or implementation steps before applying them to real projects.

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: 96% confidence
Finding: The skill description and usage condition are broad enough to match many ordinary software or data-help requests, which can cause unintended activation outside the intended AdMapix-specific scope. Over-broad routing is dangerous because it can override more appropriate skills, produce irrelevant guidance, and increase the chance that users receive incorrect or unsafe implementation advice in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list includes highly generic terms such as 'raw', 'data', 'layer', 'apps', and 'bug fix', which are common across a wide range of unrelated requests. Such ambiguous triggers substantially raise the risk of accidental invocation, causing skill hijacking or misrouting where this skill is selected instead of a safer or more specialized alternative.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences and keyword list are broad enough to match generic terms like "software-and-data," "raw," or "data," which can cause the skill to activate outside its intended AdMapix-style scope. In an agent ecosystem, unintended invocation can route unrelated user requests into the wrong workflow, leading to incorrect actions, user confusion, and possible exposure of contextual data 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 sentences are broad, natural-language phrases that could match ordinary user requests and cause the skill to activate unintentionally. Because this skill is positioned as a general helper for software/data workflows, accidental invocation could misroute user tasks, override a more appropriate skill, or expand the agent's behavior in ways the user did not explicitly request.
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 request templates that can match ordinary user language, causing the skill to activate outside its intended scope. In an agent environment, overbroad invocation can route unrelated tasks into this skill, increasing the chance of incorrect handling, prompt hijacking opportunities, or unsafe execution paths driven by mismatched context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger sentences use broad boilerplate phrases like 'Help me' and 'I need a practical workflow,' which do not establish clear invocation boundaries and reinforce ambiguous matching behavior. This makes accidental or excessive activation more likely, especially in shared agent environments where trigger examples may shape routing heuristics or user invocation patterns.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description says to use the skill when users mention broad categories like software-and-data, admapix, raw, data, or layer, without clearly defining boundaries for appropriate use. Ambiguous activation criteria increase the chance the skill is selected for unrelated requests, which can produce misleading output or bypass more suitable, safer skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include very broad generic terms such as "raw", "data", "layer", and "apps", which can match many unrelated user requests. This can cause accidental invocation of the skill in contexts it was not designed for, leading to inappropriate guidance, confusion, or unsafe delegation of tasks to a mismatched workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The default prompt is very broad and loosely scoped, using generic trigger language tied to multiple common terms and workflows. Combined with implicit invocation, this increases the chance the skill will activate in situations the user did not clearly intend, which can route requests into the wrong capability, expose unrelated context to the skill, or produce unsafe/irrelevant actions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: 该技能文件为 SKILL.zh-CN.md，全文内容以中文呈现，但未见任何自然语言说明表明这是可选语言版本、或用户可以改用其他语言。按照语言/区域政策，若技能对语言有固定约束，通常应提供用户选择或明确的适用范围说明。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The file mixes English with Chinese-language titles and Indonesian text in evidence references, but does not state whether multilingual behavior is intentional or give users a language/locale option. For skills that may surface or reuse this content, the lack of explicit language choice can conflict with a policy expectation not to force a locale without opt-in.
Content: No source excerpt is available for this finding.