Security audit

Skill Files

Security checks for vulnerabilities and agentic risk

Overview

The skill is a UI review helper, but it delegates review rules and output instructions to a mutable remote document on every run without pinning or validation.

Review this skill before installing. It is not evidence of malware, but users should be aware that each run may behave differently based on the current contents of an external GitHub document. Prefer a version that vendors or pins the guidelines and treats remote text as untrusted reference material, not agent instructions.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:12
Finding: Remote Content Is Treated as Authoritative Agent Instructions
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:19
Finding: Unpinned Mutable Remote Dependency Is Retrieved on Every Review
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are very broad and map to common user requests such as reviewing UI, accessibility, UX, or best practices, increasing the chance this skill is auto-selected in situations beyond its narrow intended scope. Overbroad activation can cause unreviewed network-fetching behavior or application of remote instructions in contexts where the user did not expect it.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill requires fetching remote content on every run and treats the fetched content as authoritative instructions, yet gives no warning that external network access will occur. This creates a supply-chain and prompt-injection risk: if the remote document is changed maliciously or unexpectedly, the skill may follow attacker-controlled instructions during routine audits.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest frames this skill as reviewing UI code for guideline compliance, but the remediation section directs the agent to run python3 skills/ui-ux-pro-max/scripts/search.py ... commands. Spawning a Python process to query another skill is not an obvious requirement of a review-only auditing skill and introduces an execution capability beyond the stated purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.