Security audit

Password Generator

Security checks for vulnerabilities and agentic risk

Overview

This local password tool has no hidden networking or persistence, but it handles real passwords in ways that can expose them and can overstate weak passphrases as acceptable.

Review before installing. Use it only for throwaway generated passwords, avoid analyzing real active passwords with the command-line interface, and do not rely on its passphrase strength labels unless the passphrase logic is fixed with a larger word list, minimum word count, and entropy-based scoring.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/password-gen.py:235
Finding: Plaintext Password Exposure Through Command-Line Arguments and Terminal Output
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/password-gen.py:101
Finding: Low-Entropy and Empty Passphrases Are Misclassified as Medium Strength
Content: View full analysis
12: w ...[truncated 2250 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrase "any password-related security needs" is broader than the documented capabilities of the skill and can cause the agent to invoke this skill for requests outside safe or intended scope. In a security-sensitive domain like passwords, overbroad routing can lead to incorrect handling of credential-management, recovery, storage, or policy questions that the skill may not actually support.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The documentation instructs users to pass existing passwords directly on the command line, which can expose secrets through shell history, terminal logging, audit trails, and process listings visible to other local users. Because this skill explicitly handles passwords, the context makes this more dangerous: users are likely to paste real credentials exactly as shown.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The tool prints generated passwords and user-supplied passwords directly to stdout during both generation and analysis. In real environments, terminal output may be captured by scrollback, shell session recording, CI logs, remote terminal logging, or shoulder-surfing, which can expose secrets unintentionally. Because this skill handles highly sensitive data by design, plaintext display materially increases disclosure risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: User-facing descriptions, help text, errors, and output labels are all presented in Chinese, and the script offers no option to select another language. This can violate language or locale policy where tools must not force a specific language without user choice or documented justification.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: SKILL.md:31