Security audit

Code Right Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: sends a system name and email to an external task service to generate software copyright materials, with no hidden persistence or local data harvesting found.

Install only if you are comfortable sending the software system name and recipient email to softcraft.cloud for document generation and email delivery; avoid using confidential project names or personal emails unless that service is acceptable for your workflow.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill describes a workflow that sends task data to an external service and delivers results by email, which clearly implies network use, but it declares no explicit tool scope or permissions. Without declared boundaries, an agent or integrator may invoke networked behavior without clear user visibility or policy enforcement, increasing the chance of unintended data disclosure or overbroad execution.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The description advertises automatic generation and email delivery but does not clearly warn users that their system name, generated materials, and contact email will be sent to external infrastructure. This is dangerous because users may disclose proprietary product information or personal data without understanding that third-party processing and outbound email are part of the workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is framed in broad, convenience-oriented language ('tell it the system name and email' and it handles the rest) without defining tight activation conditions or approval points. In agent environments, vague trigger boundaries can cause the skill to be selected or run in contexts where the user did not intend external task creation or email delivery, leading to accidental data transmission.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The entire skill title and usage description are presented only in Chinese, with no indication that users may choose another language or locale. This can violate language or locale policy where skills must not force a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.