ClawHub
Back to skill

Security audit

Explanation Docs

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-writing skill that provides templates and guidance for explanation docs and does not run code or access user data.

This skill is reasonable to install for help drafting conceptual and architecture explanation docs. Be aware it may activate on broad how/why writing requests, and it references a separate docs-style skill for full guidance, but the inspected artifact itself does not execute code or seek sensitive access.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (14)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

Connect unfamiliar concepts to things readers already know.

markdown
<!-- Good: Relatable analogy -->
Think of the message queue like a post office. Messages (letters) are dropped off
by senders and held until recipients pick them up. The post office doesn't care
about the content - it just ensures reliable delivery.

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 149)May include surrounding context.

Don't just describe what exists - explain why it exists that way.

markdown
<!-- Good: Explains rationale -->
We chose eventual consistency over strong consistency because our read-heavy
workload (100:1 read-to-write ratio) benefits more from low latency than from
immediate consistency. Most users never notice the brief delay.

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 300)May include surrounding context.

md
## Overview

Our authentication system uses short-lived access tokens with long-lived refresh
tokens. This pattern, sometimes called "token rotation," balances security with
user experience by limiting exposure while avoiding frequent re-authentication.

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 348)May include surrounding context.

md
## Overview

Our authentication system uses short-lived access tokens with long-lived refresh
tokens. This pattern, sometimes called "token rotation," balances security with
user experience by limiting exposure while avoiding frequent re-authentication.

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 351)May include surrounding context.

md
## Overview

Our authentication system uses short-lived access tokens with long-lived refresh
tokens. This pattern, sometimes called "token rotation," balances security with
user experience by limiting exposure while avoiding frequent re-authentication.

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 369)May include surrounding context.

md
## Overview

Our authentication system uses short-lived access tokens with long-lived refresh
tokens. This pattern, sometimes called "token rotation," balances security with
user experience by limiting exposure while avoiding frequent re-authentication.

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 324)May include surrounding context.

md
### Core Concepts

**Access tokens** are like day passes at a conference. They grant entry for a
limited time and are checked at each door (API endpoint). If someone steals
your day pass, they can only use it until it expires.

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 371)May include surrounding context.

md
### Core Concepts

**Access tokens** are like day passes at a conference. They grant entry for a
limited time and are checked at each door (API endpoint). If someone steals
your day pass, they can only use it until it expires.

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 337)May include surrounding context.

md
When a user logs in:

1. They provide credentials to the authentication service
2. If valid, they receive both an access token (15-minute expiry) and
   a refresh token (7-day expiry)
3. The access token is used for API requests
4. When the access token expires, the refresh token obtains a new one

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 339)May include surrounding context.

md
When a user logs in:

1. They provide credentials to the authentication service
2. If valid, they receive both an access token (15-minute expiry) and
   a refresh token (7-day expiry)
3. The access token is used for API requests
4. When the access token expires, the refresh token obtains a new one

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 340)May include surrounding context.

md
When a user logs in:

1. They provide credentials to the authentication service
2. If valid, they receive both an access token (15-minute expiry) and
   a refresh token (7-day expiry)
3. The access token is used for API requests
4. When the access token expires, the refresh token obtains a new one

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 359)May include surrounding context.

md
## Design Decisions and Trade-offs

### Why Short-Lived Access Tokens?

We chose 15-minute expiry based on our threat model. Shorter expiry limits the
window for stolen token abuse, but more frequent refreshes increase latency

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 389)May include surrounding context.

md
sessions or distributed session storage. We rejected this due to scaling
complexity and regional latency concerns.

### Longer Access Token Expiry

Longer-lived tokens reduce auth service load but increase risk from token
theft. Given our security requirements, we prioritized shorter windows.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description uses very broad trigger language such as 'when asked how/why something works,' which can cause the agent to activate on common conversational requests outside a narrowly scoped documentation task. Over-broad activation increases the chance of inappropriate tool/skill routing and unintended influence over unrelated user interactions.

Content

No source excerpt is available for this finding.