ClawHub
Back to skill

Security audit

Clawra Selfie

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent image-generation-and-messaging purpose, but it grants broad messaging and command authority with insufficient safeguards around sending and unsafe example code.

Review this skill before installing. It is not clearly malicious, but it can generate images through a third-party provider and send them to real messaging channels. Only use it in an environment where OpenClaw sending is scoped to approved channels, require explicit confirmation before dispatch, and avoid using the TypeScript exec example unless it is rewritten to pass arguments without a shell.

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 (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:311
Finding

Shell Command Injection Through OpenClaw Message Parameters

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to activate on ordinary conversational requests like 'what are you doing?' or 'send me a pic', which can cause the agent to initiate image generation and downstream message delivery without sufficiently explicit user intent. In this skill, activation is especially sensitive because it chains external API use and cross-platform message sending, increasing the chance of unintended disclosure or spam.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description does not clearly warn that user-provided context, generated image data, and destination/channel metadata will be transmitted to third-party services and messaging platforms. That omission can mislead users about where their content is going and undermines informed consent, particularly because the workflow involves both an external image-editing provider and outbound distribution.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This code sends user-influenced prompt content and the reference image URL to an external service, which is a real data egress path. In context, the transmission is part of the skill's intended function, but it remains security-relevant because users may not realize their requests are being sent off-platform to a third party for processing.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

md
--arg prompt "$PROMPT" \
  '{image_url: $image_url, prompt: $prompt, num_images: 1, output_format: "jpeg"}')

curl -X POST "https://fal.run/xai/grok-imagine-image/edit" \
  -H "Authorization: Key $FAL_KEY" \
  -H "Content-Type: application/json" \
  -d "$JSON_PAYLOAD"

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This is another concrete outbound transmission of user-derived content to fal.run for image editing, creating the same external data exposure risk in the complete script example. Because the skill later forwards the resulting image to messaging channels, this egress becomes more dangerous in context by enabling a full generate-and-distribute pipeline from loosely validated input.

Content

Scanner excerpt · SKILL.md (reported line 209)May include surrounding context.

md
--arg prompt "$EDIT_PROMPT" \
  '{image_url: $image_url, prompt: $prompt, num_images: 1, output_format: "jpeg"}')

RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image/edit" \
  -H "Authorization: Key $FAL_KEY" \
  -H "Content-Type: application/json" \
  -d "$JSON_PAYLOAD")

Static analysis

No suspicious patterns detected.