ClawHub
Back to skill

Security audit

CamScanner Detect Tampering

Security checks for vulnerabilities and agentic risk

Overview

This skill sends a user-selected image to CamScanner to check for editing, and that external processing is disclosed and aligned with its stated purpose.

Install only if you are comfortable sending images to CamScanner's servers for analysis. Avoid using it for highly sensitive, regulated, or confidential images unless that third-party processing is acceptable under your policies.

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This step uploads the user's local image bytes to an external third-party service. Even though the skill discloses the data flow and the transmission is necessary for the advertised functionality, it still creates a real privacy and data-exfiltration risk because potentially sensitive images leave the local environment and are processed by a remote server.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

bash
BASE="https://ai-tools.camscanner.com"

IN_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/upload_file/execute" \
  -H "Content-Type: application/octet-stream" \
  --data-binary "@/path/to/image.jpg" | jq -r '.tool_result.data.file_id')

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

Step 2: Validate Image (Detect Tampering)

bash
curl -sS -X POST "$BASE/v1/tools/validate_image/execute" \
  -H "Content-Type: application/json" \
  -d "{\"file_id\":\"$IN_FILE_ID\",\"validate_mode\":1}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

Step 2: Validate Image (Detect Tampering)

bash
curl -sS -X POST "$BASE/v1/tools/validate_image/execute" \
  -H "Content-Type: application/json" \
  -d "{\"file_id\":\"$IN_FILE_ID\",\"validate_mode\":1}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This is a second example of the same behavior in the quick-reference pipeline: uploading a user-supplied image to CamScanner's external servers. Because images may contain personal, confidential, or regulated information, sending them off-device is a genuine data exposure risk even when it is part of the intended feature.

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

md
INPUT_IMAGE="/path/to/image.jpg"

# Upload
IN_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/upload_file/execute" \
  -H "Content-Type: application/octet-stream" \
  --data-binary "@$INPUT_IMAGE" | jq -r '.tool_result.data.file_id')

Static analysis

No suspicious patterns detected.