Go Code Review

• Outcome: Pass
• Latest audit: Sep 14, 2026 · 11:22 PM UTC
• Version: 2.3.1

Overview

This Go code-review skill is a markdown-only review checklist with no executable behavior, though it depends on a sibling verification skill that users should trust separately.

This skill appears safe to install as a Go review aid. Before relying on it, confirm that the referenced sibling review-verification-protocol skill is present, trusted, and reviewed, because that separate file can affect the review process.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:22

Finding

Mandatory Unbundled Skill Dependency Can Alter Review Behavior

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 22-23
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable Code Snippet:

markdown

4. **Pre-report verification** — Load and follow [review-verification-protocol](../review-verification-protocol/SKILL.md).  
   **Pass:** The protocol’s **Pre-Report Verification Checklist** is satisfied for each finding you will report (actual code read, surrounding context checked, “wrong” vs “different style” distinguished, etc.).

The requirement is reiterated at line 154:

markdown

Satisfy **step 4** in [Review Workflow](#review-workflow): load [review-verification-protocol](../review-verification-protocol/SKILL.md) and complete its pre-report checks for each issue.

Technical Analysis

The Skill mandates loading and following instructions from ../review-verification-protocol/SKILL.md, a sibling path outside the audited project. That dependency is not included in the supplied package and therefore cannot be reviewed, integrity-checked, or version-pinned as part of this audit.

Because the referenced file contains agent instructions rather than passive data, changing it can directly modify the effective behavior of this Skill. A malicious or compromised sibling Skill could instruct the agent to suppress legitimate findings, produce misleading results, access unrelated resources, or perform other actions beyond the intended Go code-review workflow.

Attack Path

1. An attacker gains the ability to create or modify the sibling file at ../review-verification-protocol/SKILL.md.
2. A user invokes this Go code-review Skill.
3. The workflow reaches its mandatory pre-report verification step.
4. The agent loads and follows the attacker-controlled sibling Skill as required by SKILL.md.
5. The injected instructions influence the review process or final report, potentially suppressing findings or directing unintended ac ...[truncated 720 chars]

Remediation

View remediation

Remediation Suggestions

1. Bundle the verification protocol inside this project so it is reviewed and distributed with the primary Skill.
2. Replace the parent-directory reference with a package-local path, such as references/review-verification-protocol.md.
3. If an external dependency is unavoidable, pin it to a trusted immutable version and verify its content using a cryptographic hash before loading it.
4. Document the dependency’s trusted source, version, update process, and ownership.
5. Explicitly state that dependency instructions cannot override system, developer, user, security, or least-privilege constraints.
6. Treat missing or failed integrity verification as a hard failure rather than loading an unverified replacement.
7. Include the dependency in future security audits and review all updates before deployment.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.