Security audit

代码

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a code formatter/reviewer, but it asks for broad file search, file write, and command execution authority without tight limits.

Review this skill before installing. It is not evidence of malware, but it grants more authority than a formatter normally needs. Use it only in repositories you are comfortable letting an agent search and edit, and do not allow command execution unless you explicitly understand the command and its inputs.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill declares exec even though the documented function is code formatting/review/fixing, which can usually be performed on provided text without shell execution. This unnecessarily expands the attack surface: a user or prompt-injected code sample could steer the agent into running local commands, causing command execution or data exposure in contexts where execution was never needed.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Declaring glob and grep gives the skill repository-wide discovery and search capability beyond the clearly stated need to review supplied ObjectScript content. In an agent setting, these tools can be abused to enumerate files, inspect unrelated project content, or exfiltrate secrets and proprietary code under the pretext of formatting assistance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The activation description is overly broad, including generic development assistance, debugging, testing, and deployment scenarios rather than a tightly scoped formatting/review role. Over-broad routing increases the chance this skill is auto-invoked for unrelated requests, where its powerful file and execution tools could be used in ways the user did not intend.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.