Back to skill

Security audit

Sombra — Reader Mode for AI

Security checks for vulnerabilities and agentic risk

Overview

The skill’s reader-library purpose is coherent, but its setup asks users to run an unpinned remote MCP package and pass a reusable token in plaintext command arguments.

Review this before installing. Prefer a pinned and reviewed `sombra-mcp` version, avoid placing long-lived tokens directly in shared config or process arguments, use OAuth or a secret manager if available, issue a narrow-scope token, and run the MCP server with only the local and network access it needs.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:40
Finding

Unpinned Third-Party Package Is Automatically Downloaded and Executed

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:36
Finding

Personal Access Token Is Stored in Configuration and Passed Through Process Arguments

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## Setup

### 1. Get a Personal Access Token

Sign up at [sombra.so](https://sombra.so) and create a token in **Settings > Access Tokens**.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
### 1. Get a Personal Access Token

Sign up at [sombra.so](https://sombra.so) and create a token in **Settings > Access Tokens**.

### 2. Configure OpenClaw

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to launch an MCP server via npx without pinning an exact package version or integrity mechanism. This creates a supply-chain risk: a future malicious or compromised package release could be pulled and executed automatically in the user's environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The setup example places a bearer token directly on the command line as an argument to npx. Command-line arguments are often exposed through shell history, process listings, logs, crash reports, and telemetry, which can leak reusable credentials to other local users or monitoring systems.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The recommended workflow examples use generic natural-language requests such as "Research rate limiting approaches...", "Save it to my... collection", and "Read the context from my... collection" without defining explicit invocation boundaries or exclusions. In a skill description, these broad phrases could overlap with ordinary conversation and make it unclear when the skill should activate versus when the user is just discussing work.

Content

No source excerpt is available for this finding.