ClawHub
Back to skill

Security audit

de-ai-ify

Security checks for vulnerabilities and agentic risk

Overview

This writing helper is cloud-backed and sends the user-selected document text to SkillBoss for rewriting, which is disclosed and fits its purpose but needs privacy caution.

Only use this skill on files you are comfortable sending to SkillBoss API Hub. Avoid confidential drafts, proprietary documents, credentials, or regulated data unless you trust that service's privacy and retention practices.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly describes reading a user file, creating a copy, and sending the file contents to a third-party API, but it does not present a clear privacy warning, consent step, or data-handling disclosure to the user. That creates a real confidentiality risk because users may provide sensitive drafts, internal documents, or proprietary text without realizing the content leaves the local environment.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The request to the external API includes authentication headers and sends text to a third-party endpoint for transformation. While this is consistent with the skill's functionality, it is still a true security concern because the document data leaves the trusted boundary and may be logged, retained, or mishandled by the service.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def de_ai_ify(text: str) -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The request to the external API includes authentication headers and sends text to a third-party endpoint for transformation. While this is consistent with the skill's functionality, it is still a true security concern because the document data leaves the trusted boundary and may be logged, retained, or mishandled by the service.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def de_ai_ify(text: str) -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The hardcoded external endpoint confirms that processing occurs on a remote third-party service rather than locally. In this skill context, that increases the chance of unintentional disclosure of confidential writing, source material, or internal business text, especially because the skill is marketed as a simple editing transformation.

Content

Scanner excerpt · SKILL.md (reported line 109)May include surrounding context.

md
def de_ai_ify(text: str) -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
            "Content-Type": "application/json"

Static analysis

No suspicious patterns detected.