Security audit

Software Data Admapix Raw Developer Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording, but I found no hidden execution, persistence, credential handling, or destructive behavior.

Before installing, be aware that this skill may be selected for unrelated requests that mention common words like data or raw. Install is reasonable if you want an AdMapix-style workflow helper, but the publisher should narrow the trigger phrases to make invocation more predictable.

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: 96% confidence
Finding: The skill description says to use the skill when a user asks for very broad terms like "software-and-data," "raw," "data," or needs almost any "workflow, artifact, checklist, analysis, or implementation support." This can cause accidental invocation for unrelated requests, expanding the skill's reach beyond its intended scope and potentially surfacing unsafe or irrelevant instructions in contexts where they were not requested.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include highly generic terms such as "raw," "data," "layer," "apps," and "bug fix" without any qualifying context. These terms are common across many domains, so they materially increase the chance of unintended invocation and routing, which can lead to inappropriate tool behavior, context pollution, or bypass of safer domain-specific handling.
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 highly generic phrase ('Help me') and then appends long requirement text, which makes invocation boundaries unclear and increases the chance the skill is activated for unrelated software/data requests. In an agent ecosystem, broad triggers can cause unintended routing, exposing users to irrelevant or overly powerful workflows without clear consent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence is phrased as a broad, natural-language request that could match ordinary user prompts outside the intended AdMapix/raw-data workflow. Overly permissive activation increases the chance of unintended skill invocation, which can route unrelated user tasks into this skill and cause incorrect actions, data handling, or prompt-scope confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This trigger uses a generic request form ('I need a practical workflow for ...') that is common in benign user conversation and lacks strong domain boundaries. In an agent environment, such generic phrasing can cause accidental invocation and make the skill capture requests it was not designed to handle, reducing predictability and safety.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are extremely generic (for example, 'Help me...' and 'I need a practical workflow...') and can match a wide range of ordinary user requests unrelated to this skill. In an agent-routing context, this can cause unintended invocation, prompt hijacking of normal workflows, or the skill being selected when a more appropriate and safer tool should handle the request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences are vague and resemble ordinary user requests, making them poor discriminators for safe activation. Because they normalize broad natural-language invocation, they reinforce ambiguous matching behavior and make accidental activation more likely in unrelated conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger keyword list includes very generic terms such as "raw," "data," "layer," and likely common domain words that can appear in many unrelated user requests. This can cause the skill to activate unexpectedly, leading to misrouting, prompt confusion, and unsafe over-application of the skill outside its intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example trigger phrases are broad natural-language requests that resemble ordinary user prompts and do not clearly distinguish skill-specific invocation from general conversation. That increases the chance of accidental activation or ambiguous routing, especially in systems that match examples heuristically.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The default prompt is broad and generic, which can cause the skill to be invoked in situations beyond the author’s intended scope. Combined with allow_implicit_invocation=true, this increases the chance of accidental routing, confusing users, or applying the skill to unrelated requests where it may expose unsafe guidance or unreliable outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger sentence 'I need a practical workflow for ...' is still broad and ambiguous because 'practical workflow' applies to many benign requests outside this skill's intended scope. This can lead to accidental invocation and misrouting, especially because the skill description covers a wide range of outputs such as artifacts, checklists, analysis, and implementation support.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The README states the skill is split into English and Chinese instruction and guide files, but it does not tell users how language selection is determined or offer an explicit opt-in choice. This can create a locale-policy concern if the skill defaults users into a language variant without user preference being established.
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 entirely presented in Chinese while describing user-facing usage and trigger guidance, but it does not indicate that the language is optional or region-specific. That can violate language/locale policy if users are not given a choice or a justification for the locale constraint.
Content: No source excerpt is available for this finding.