ClawHub
Back to skill

Security audit

qui-clawd-docs-v2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper that mostly reads local ClawdBot docs and uses a disclosed API key for optional remote documentation fetches.

Install only if you are comfortable letting the agent use SkillBoss API Hub to fetch missing ClawdBot documentation pages. Use a scoped or low-privilege API key where possible, watch quota or billing, and remember that requested documentation URLs will be sent to api.heybossai.com when local snippets or cache entries are not enough.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (11)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to make external scraping requests using a bearer token from an environment variable, but it does not require user awareness or consent before transmitting prompts/URLs to a third-party service. In an agent-skill context, silent network access plus credential use is a real security and privacy risk because user queries and operational metadata may be sent off-host unexpectedly.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
95% confidence
Finding
This finding is a duplicate representation of the same external transmission behavior at line 80 and remains a true issue in context. The main risk is silent outbound communication to a third-party service using privileged authentication in an agent workflow.

External Transmission

Medium
Category
Data Exfiltration
Content
**Example:**
```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
94% confidence
Finding
This duplicate example again shows authenticated POST-based external transmission. While not malicious on its face, it promotes a pattern that can expose user-derived content or operational context to an external provider without clear safeguards.

External Transmission

Medium
Category
Data Exfiltration
Content
If you can't find what you need:

```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
95% confidence
Finding
This duplicate finding points to the same fallback external transmission logic. Because it can retrieve broader documentation content via a third-party API, the surrounding skill context makes it moderately risky even though its stated purpose is benign documentation access.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
95% confidence
Finding
This finding is a duplicate representation of the same external transmission behavior at line 80 and remains a true issue in context. The main risk is silent outbound communication to a third-party service using privileged authentication in an agent workflow.

External Transmission

Medium
Category
Data Exfiltration
Content
**Example:**
```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
94% confidence
Finding
This duplicate example again shows authenticated POST-based external transmission. While not malicious on its face, it promotes a pattern that can expose user-derived content or operational context to an external provider without clear safeguards.

External Transmission

Medium
Category
Data Exfiltration
Content
If you can't find what you need:

```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
Confidence
95% confidence
Finding
This duplicate finding points to the same fallback external transmission logic. Because it can retrieve broader documentation content via a third-party API, the surrounding skill context makes it moderately risky even though its stated purpose is benign documentation access.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
        "type": "scraper",
Confidence
93% confidence
Finding
The hardcoded external domain confirms that the skill is designed to communicate with a third-party service. In a security review, an explicit remote endpoint tied to authenticated scraping is a real concern because it expands the trust boundary and can transmit sensitive context off-system.

External Transmission

Medium
Category
Data Exfiltration
Content
**Example:**
```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
        "type": "scraper",
Confidence
93% confidence
Finding
This example repeats the explicit third-party endpoint usage and therefore confirms the same trust-boundary expansion. Even as sample code, it encourages external transmission patterns that may expose data beyond the local environment.

External Transmission

Medium
Category
Data Exfiltration
Content
```python
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={
        "type": "scraper",
Confidence
93% confidence
Finding
The fallback example again targets the same external domain for a broader refresh operation. This compounds the concern because a recovery path should not silently expand external communication scope without explicit user approval.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
```python
import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

result = requests.post(
    "https://api.heybossai.com/v1/pilot",
Confidence
90% confidence
Finding
The skill explicitly reads a secret from the environment and uses it to authenticate outbound requests. In agent environments, requesting or consuming environment secrets is sensitive because it normalizes secret access within skill logic and can enable misuse, credential leakage, or unauthorized third-party actions if the skill is modified or abused.

Static analysis

No suspicious patterns detected.