Security audit

Snail Mail

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local operator inbox with disclosed local storage and no network behavior, but users should treat stored and rendered messages as potentially sensitive.

Install only if you want agents to keep a local inbox of operational notes. Keep the workspace private, avoid storing secrets or credentials in messages, and be cautious rendering untrusted content to Slack or Discord because formatting and mentions may not be escaped.

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 (3)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/inbox.js:212
Finding: Unescaped User-Controlled Content in Markdown Rendering
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/inbox.js:27
Finding: Predictable Temporary File Allows Symlink-Based File Overwrite
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/inbox.js:19
Finding: Potentially Sensitive Inbox Data Uses Umask-Dependent Permissions
Content: View full analysis
Remediation: View remediation

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)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger guidance says the operator asking to see their inbox or saying 'inbox', 'messages', or 'check inbox' should cause the skill to run. Terms like 'messages' are overly generic and can be invoked accidentally during ordinary conversation, causing unintended data disclosure or stateful actions in the wrong context.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.