Security audit

Emoji Wrapper

Security checks for vulnerabilities and agentic risk

Overview

This emoji skill does what it claims, but it processes every incoming message through an unverified neighboring dependency, which is broader than simple marker replacement needs.

Install only if you are comfortable with every message in enabled conversations being inspected by this wrapper and its local-auto-emoji dependency. Prefer a reviewed or pinned local-auto-emoji installation, and avoid enabling it in chats that may contain sensitive content unless the skill is updated to prefilter marker-free messages and constrain dependency loading.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: script.py:14
Finding: Unverified Dependency Execution Through Python Search-Path Manipulation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: script.py:119
Finding: Unnecessary Disclosure of Complete Messages and Session Identifiers to an External Dependency
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill modifies user-visible message output and sends media, but the description does not clearly warn users that their text may be transformed and that additional image content will be emitted. This lack of transparency can lead to surprising behavior, privacy concerns, or unintended media generation in contexts where message fidelity matters.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill documentation states it 'intercepts all incoming messages' without defining scope, opt-in conditions, or trigger boundaries. A wrapper that processes every message can unexpectedly alter unrelated content and expand the skill's effective access surface, which is risky even if the intended behavior is only emoji substitution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The documented marker format is presented only with Chinese examples like [标记], [可爱], and [眨眼], with no indication that other languages are supported or that this is an opt-in locale constraint. That can amount to a language-policy issue if users are implicitly expected to use a specific language.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.