ClawHub
Back to skill

Security audit

Diffbot

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Diffbot connector use is coherent, but its first-time setup tells agents to run unverified remote installer scripts directly in a shell.

Install only if you are comfortable using OOMOL as the Diffbot access layer and avoid letting an agent run the provided remote installer commands automatically. Prefer installing the oo CLI through a verified, versioned method you can inspect, then sign in and connect Diffbot deliberately before using the skill.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:55
Finding

Unverified Remote Installation Scripts Executed Directly by Shells

Content
View full analysis
Remediation
View remediation
oo-cli.tar.gz" | sha256sum --check - # Inspect and install only after successful verification and explicit approval. ``` Equivalent signature or checksum verification should be provided for Windows rather than passing network content to `Invoke-Expression`. ]]>

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into bash, which is a classic unsafe pattern because any compromise of the host, CDN, DNS, TLS termination, or distribution pipeline can result in arbitrary code execution. Since this appears in a fallback path the agent may follow automatically when oo is missing, the skill context increases the danger by normalizing execution of unverified code on the user's system.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY Diffbot request" and "Whenever a task involves Diffbot," which is a very broad trigger that could overlap with ordinary discussion or indirect references to Diffbot. It does not provide scope boundaries or negative examples clarifying when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.