receiving-code-revie

• Outcome: Review
• Latest audit: Aug 14, 2026 · 11:06 AM UTC
• Version: 1.0.0

Overview

This skill is framed as code-review help but gives broad automation, API credential, file, and command-execution instructions that are not clearly scoped to that purpose.

Review this carefully before installing. It does not show destructive code or a runnable payload, but it asks for broad read/exec authority and describes credential, API, file, and command workflows that are not clearly tied to code-review feedback. Use only with explicit per-action confirmation and avoid providing API keys or credentials unless the publisher supplies precise endpoints, data flows, and a bounded workflow.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The manifest presents the skill as a narrowly scoped aid for scrutinizing code review feedback, but the body describes unrelated generic automation and data-processing behavior. This mismatch can mislead users and downstream agents into granting trust, permissions, or invocation in contexts the skill was not expected to handle, increasing the chance of unsafe execution paths.

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The documentation introduces API integration, external data sources, and connectivity requirements that are not justified by a skill meant to evaluate review feedback. Unnecessary network and credential-related scope expands the attack surface and can normalize external data access or secret use where none should be needed.

Context-Inappropriate Capability

High

• Confidence: 98% confidence
• Finding: The skill instructs users to configure API keys, establish connections, prepare files, and execute commands despite being framed as a verification aid for code review feedback. This is dangerous because it can induce secret exposure and system-state changes under a misleadingly low-risk skill label, especially with the declared exec capability.

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: The skill broadens from careful review-feedback verification into general automation, data analysis, batch processing, format conversion, and orchestration. In the context of an agent skill, this scope creep is dangerous because a seemingly innocuous review assistant may be invoked with broader authority than users expect, enabling actions beyond the intended trust boundary.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger condition states the skill activates when the user needs 'related operations,' which is too vague to establish safe invocation boundaries. Ambiguous activation increases the likelihood that the skill is selected in inappropriate contexts and may perform higher-risk actions than the user intended.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill references API calls, command execution, file handling, and credential setup without clearly warning that these actions can expose secrets, alter files, or affect the host system. In a skill marketed as review-feedback verification, the lack of transparent impact disclosure creates a meaningful safety risk because users may consent without understanding the operational consequences.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.