Security audit

Software Data Admapix Raw Developer Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only helper with no executable or persistent behavior, though its broad triggers may cause accidental activation.

Install only if you want a broad AdMapix-style developer workflow helper, and consider narrowing or disabling implicit invocation so ordinary software, data, or bug-fix requests do not route to this skill unintentionally.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad and generic enough to match ordinary requests about software, data, bug fixing, or practical workflows, which can cause unintended invocation of the skill outside its intended scope. In an agent ecosystem, over-broad activation increases the chance of prompt-routing mistakes, inappropriate handling of unrelated tasks, and accidental exposure of users to instructions or workflows they did not request.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrases are broad enough to match ordinary software-help requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the risk of misrouting user tasks, unexpected execution paths, and accidental invocation on sensitive development or data-handling requests.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill description defines activation using a very broad mix of generic concepts like software, data, workflow, artifact, checklist, analysis, and implementation support. That can cause the skill to activate outside its intended scope, creating prompt-routing confusion and increasing the chance that unrelated user requests are handled by an overly specialized or mismatched skill. In agent systems, ambiguous routing can degrade safety controls by invoking instructions and context the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list includes highly generic terms such as raw, data, layer, apps, and bug fix, which are common across many unrelated requests. In a keyword-triggered skill system, this can cause accidental invocation at high frequency, leading to misrouting, context pollution, and possible interference with safer or more appropriate skills. Because trigger matching is often automated, overly broad keywords are especially risky operationally.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation while the manifest lacks specific activation wording makes unintended automatic selection much more likely. Because this skill is framed as a broad developer helper for workflows, bugs, safety, reliability, and adjacent implementations, it can overreach into many normal software conversations and be triggered without clear user consent or relevance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a generic everyday phrase ('Help me ...'), which is likely to cause unintended activation for many unrelated user requests. In a skill-routing system, overly broad triggers can hijack normal conversations and invoke this skill outside its intended scope, creating misrouting, irrelevant actions, and confusion that may propagate into downstream workflow or code assistance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This file is presented as a Chinese README, but key usage and workflow instructions are written in English, including the trigger phrases and core description. That creates an implicit language constraint or mismatch without user opt-in, which can violate language/locale expectations for the documented skill interface.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example trigger sentences are vague and effectively restate the broad requirement rather than demonstrating a bounded activation condition. This reinforces imprecise routing behavior and may teach maintainers or trigger-generation systems to invoke the skill for loosely related requests. While not directly code-execution dangerous, it increases the likelihood of incorrect skill selection and downstream unsafe handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list includes overly broad everyday terms such as "raw", "data", and "layer", which can cause the skill to activate in many unrelated conversations. Unintended invocation can override more appropriate skills, expose users to irrelevant or risky workflow guidance, and expand the attack surface for prompt-routing abuse.
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 are generic and permissive, using broad constructions like "Help me" and "I need a practical workflow" without clear scope boundaries. This encourages loose matching behavior and increases the chance that normal user requests will incorrectly route into this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt is extremely broad and generic, using common software-help phrasing without meaningful boundaries on when the skill should activate. In practice, this can cause the agent to invoke the skill in unrelated conversations, increasing the chance of prompt-scope hijacking, unexpected tool behavior, or unsafe handling of user data in contexts the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger sentence is ambiguous because it does not clearly define what inputs, tasks, or contexts should activate the skill, making routing decisions imprecise. This increases the chance that unrelated software/data requests get matched to this skill, which is especially risky because the skill claims a broad implementation-support role and could be selected in situations where a more appropriate or safer skill should handle the request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The file lists separate English and Chinese instruction and guide files, but does not state that the user can choose their preferred language or that language selection is optional. Under the language/locale policy, fixed language behavior should be explicitly user-driven or justified.
Content: No source excerpt is available for this finding.