Security audit

密码生成器

Security checks for vulnerabilities and agentic risk

Overview

This password generator skill asks for broader computer access and describes unrelated security, audit, and password-storage features, so it should be reviewed before installation.

Install only if you are comfortable reviewing and constraining the agent's use of this skill. It should be narrowed to explicit password-generation requests, remove unrelated audit and threat-intelligence claims, and avoid read/write/exec authority unless a specific user-directed export workflow is clearly scoped.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Description-Behavior Mismatch

Medium

Confidence: 96% confidence
Finding: The skill is presented as a password generator, but its documented output schema describes grading, scoring, and security-review style results rather than generated passwords. This mismatch can mislead an agent into invoking the skill in the wrong context or trusting outputs that are unrelated to the claimed function, which increases the risk of unsafe automation and hidden behavior.

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The manifest markets a simple password generator, but the body advertises unrelated capabilities such as CVE correlation, compliance auditing, asset risk scoring, and threat-intelligence alerting. This capability drift is dangerous because it can conceal broader operational behavior than users or agents would reasonably expect from the declared purpose.

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The documentation claims password validation, storage, management, and reset capabilities beyond simple generation. Expanding a security-sensitive skill into adjacent password-handling operations without clear boundaries raises the risk that secrets may be stored, processed, or transmitted in ways users did not intend.

Context-Inappropriate Capability

High

Confidence: 97% confidence
Finding: The manifest also requests read and write capabilities even though basic password generation should not need filesystem access. Unnecessary file permissions create opportunities to read sensitive local data or persist generated passwords or other secrets to disk without clear user expectation.

Context-Inappropriate Capability

Medium

Confidence: 97% confidence
Finding: The manifest also requests read and write capabilities even though basic password generation should not need filesystem access. Unnecessary file permissions create opportunities to read sensitive local data or persist generated passwords or other secrets to disk without clear user expectation.

Vague Triggers

High

Confidence: 95% confidence
Finding: The activation guidance is overly broad, telling agents to use the skill for generic efficiency, automation, batching, and workflow optimization rather than only for password generation. This can cause inappropriate invocation in unrelated contexts, increasing the chance that privileged tools are exposed or misused where they are not needed.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The metadata mixes clear password-generation triggers with vague, generic usage language, making invocation conditions ambiguous. Ambiguous routing is risky because agents may select this skill when a user did not ask for password generation, unnecessarily exposing file or execution capabilities.

Static analysis

No suspicious patterns detected.