Security audit

text-stats

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple text statistics helper that reads provided text or a user-selected file and does not show hidden, persistent, network, credential, or destructive behavior.

Install this only if you want an agent to compute basic statistics for text you provide. When using file mode, provide only files you are comfortable having read for this calculation.

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 instructs the agent to read a user-supplied file path via `python scripts/text_stats.py <文件路径>`, which implies file-read capability, but no corresponding permission is declared. Undeclared file access weakens security boundaries and can lead to unintended access to sensitive local files if the skill is invoked on arbitrary paths.

Vague Triggers

Medium

Confidence: 79% confidence
Finding: The trigger description is broad enough to match many generic requests involving text, files, or word counts, which increases the chance of over-invocation. Overly broad routing can cause the skill to process unintended user content or files, including cases where a different, more tightly scoped skill should handle the request.

Static analysis

No suspicious patterns detected.