ClawHub
Back to skill

Security audit

decidealot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper for sending bounded decision requests to a user-chosen local Decidealot service, with some deployment cautions but no evidence of hidden or malicious behavior.

Before installing, use a trusted Decidealot endpoint, set an API key whenever traffic leaves loopback, and prefer a pinned Docker image tag or digest for long-running deployments.

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 (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The deployment example runs psyb0t/decidealot:latest, which is a mutable tag and can change over time without notice. This creates a supply-chain and reproducibility risk: future deployments may pull a different image than the one originally reviewed, potentially introducing unvetted code or breaking changes.

Content

No source excerpt is available for this finding.

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 · references/setup.md (reported line 28)May include surrounding context.

The first start downloads model files and can take several minutes. Wait for this to return successfully before using the API:

bash
curl --fail --show-error http://127.0.0.1:8080/health

Use an immutable vX.Y.Z image tag for a lasting deployment. The full hardening and CUDA recipes are in Deployment.

Static analysis

No suspicious patterns detected.