Security code review

• Outcome: Review
• Latest audit: Sep 10, 2026 · 9:58 AM UTC
• Version: 1.0.0

Overview

This skill is a security-review checklist and its risky-looking strings are examples of vulnerabilities to find, not commands to run.

Installers should understand that this skill will guide an agent to read repository files and use read-only command-line inspection for security reviews. If using workflows that generate report artifacts, confirm whether file creation under .shield_security/ is acceptable in your workspace.

A.I.G

Vulnerability Patterns

• 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
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Unvalidated Output Injection

High

• Category: Output Handling
• Confidence: 65% confidence

Finding

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

jsx

            function UserBio({ bio }) {
              // This is a classic XSS vulnerability
              return <div dangerouslySetInnerHTML={{ __html: bio }} />;
            }
            ```
    *   **Command Injection:** Flag any use of shell commands ( e.g. `child_process`, `os.system`) that includes user input directly in the command string.

Tool Parameter Abuse

High

• Category: Tool Misuse
• Confidence: 90% confidence

Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md

*   **Vulnerable Example (Look for this pattern):**
            ```python
            import os
            # User can inject commands like "; rm -rf /"
            filename = user_input
            os.system(f"grep 'pattern' {filename}")
            ```

Tool Parameter Abuse

High

• Category: Tool Misuse
• Confidence: 85% confidence

Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md

*   **Vulnerable Example (Look for this pattern):**
            ```python
            import os
            # User can inject commands like "; rm -rf /"
            filename = user_input
            os.system(f"grep 'pattern' {filename}")
            ```

Tool Parameter Abuse

High

• Category: Tool Misuse
• Confidence: 90% confidence

Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md

*   **Vulnerable Example (Look for this pattern):**
            ```python
            import os
            # User can inject commands like "; rm -rf /"
            filename = user_input
            os.system(f"grep 'pattern' {filename}")
            ```

Chaining Abuse

High

• Category: Tool Misuse
• Confidence: 75% confidence

Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md

*   **Vulnerable Example (Look for this pattern):**
            ```python
            import os
            # User can inject commands like "; rm -rf /"
            filename = user_input
            os.system(f"grep 'pattern' {filename}")
            ```

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The document says the analyst "MUST only use read-only tools" such as ls -R, grep, and read-file at L022, but immediately states at L023 that artifacts created during security analysis should be stored in .shield_security/, which requires writing files. This is an active contradiction in the skill's operational instructions and could cause an agent to violate the intended read-only constraint.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: SKILL.md:37