ClawHub
Back to skill

Security audit

DeepRead BYOK

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only DeepRead setup skill whose key and document handling are disclosed and aligned with its BYOK purpose.

Install only if you are comfortable giving DeepRead your provider API key through its dashboard and sending documents to DeepRead's API. Prefer using environment variables or a secrets manager over reading keys from a .env file, and use scoped or revocable provider keys where possible.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
85% confidence
Finding

The skill includes a shell snippet that reads a secret directly from a local .env file using grep. In an agent context, encouraging direct access to .env increases the chance of unnecessary credential harvesting from local files, expands exposure of secrets beyond the current process environment, and may fail if .env contains additional sensitive material or malformed content. This is not overtly malicious, but it normalizes unsafe secret-handling practice.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

Nothing changes in your code. Same endpoints, same X-API-Key header:

bash
DR_API_KEY=$(grep ^DEEPREAD_API_KEY .env | cut -d= -f2)

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DR_API_KEY" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 78)May include surrounding context.

bash
DR_API_KEY=$(grep ^DEEPREAD_API_KEY .env | cut -d= -f2)

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DR_API_KEY" \
  -F "file=@document.pdf"

Static analysis

No suspicious patterns detected.