Security audit

Code Quality

Security checks for vulnerabilities and agentic risk

Overview

This code-quality skill is not clearly malicious, but it asks for shell execution while advertising broad deployment and operational security capabilities without meaningful limits or controls.

Review this skill carefully before installing. It may be reasonable for controlled code-review and test-running workflows, but only if you are comfortable granting shell execution and if the publisher clarifies that deployment, protection-rule rollout, and threat-intelligence functions require explicit user approval and narrow scope.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest markets the skill as a code-quality assistant, but the content broadens into deployment, debugging/testing, vulnerability intelligence, and operational security capabilities. This scope mismatch can mislead users and agent policy systems into granting the skill access or trust appropriate for a low-risk reviewer while it implicitly claims much more powerful security and operational behavior.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The premium feature list includes deep vulnerability scanning, CVE correlation, asset risk scoring, threat-intelligence alerting, and zero-day detection/protection rule rollout, which substantially exceed ordinary code-quality review. In the context of an agent skill, such claims can justify or normalize elevated privileges and operational actions that are not supported by the declared scope, making misuse or overpermissioning more likely.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation description is extremely broad, covering code generation, programming assistance, debugging, testing, and deployment. Overbroad triggering criteria can cause the skill to activate in many unrelated development contexts, increasing the chance that an execution-capable skill is invoked when not needed and expanding exposure to prompt injection or accidental actions.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill declares the exec tool even though the documented purpose is primarily code-quality guidance and review. Granting command execution to a broadly-scoped review skill increases the attack surface: prompts or downstream instructions could cause filesystem, network, or shell actions that are unnecessary for the stated function.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The summary is presented only in Chinese while the rest of the skill metadata and content are mixed-language, and there is no statement offering the user a language choice. This creates a language-policy concern because the skill appears to assume a specific output or interaction language without explicit user opt-in or justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.