Security audit

生产隐患排查技能

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local safety-inspection recordkeeping tool whose file writes are disclosed and match its stated purpose.

Before installing, understand that this skill will create and update local inspection and remediation records in ./inspection_data/. Use it in a workspace where those records belong, and review changes before relying on them for operational or compliance reporting.

SkillSpector

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill declares 'no external dependencies' and documents scripts that read and write local files under ./inspection_data/, but it does not declare any permissions or capability boundaries. Undeclared file read/write is risky because an agent or platform may execute the skill with broader filesystem access than users expect, enabling unintended access, overwrite, or persistence beyond the intended data directory.

Vague Triggers

Medium

Confidence: 80% confidence
Finding: The trigger conditions are broad ('daily inspection, hazard reporting, remediation tracking, periodic report generation') and do not define invocation boundaries, approval requirements, or when write operations are allowed. In agentic environments, vague triggers can cause the skill to be invoked in the wrong context and perform unintended record creation or modification, especially because it includes persistent file writes and task updates.

Static analysis

No suspicious patterns detected.