ClawHub
Back to skill

Security audit

discord-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned but should be reviewed because it sends Discord conversation summaries to an external persistent memory service without clear consent, scope, or retention guidance.

Install only if the Discord server or workspace explicitly authorizes storing conversation summaries in BlueColumn. Avoid using it for private channels, direct messages, secrets, personal data, or moderation-sensitive content unless retention and deletion controls are understood.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs agents to store Discord conversation content in an external persistent memory service, but it provides no user-facing warning, consent step, or guidance to avoid storing sensitive or personal data. In the context of Discord, conversations often contain identifiers, private messages, moderation details, or other sensitive community data, so silent persistence to a third party creates a real privacy and compliance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This skill demonstrates sending conversation text to an external endpoint (/agent-remember) using an authorization token, which is a genuine external data transmission path. While external transmission is core to the skill's purpose rather than inherently malicious, it becomes dangerous because the transmitted payload can contain Discord conversation content and the skill does not impose safeguards such as consent, data minimization, or restrictions on sensitive content.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

Store

bash
curl -X POST .../agent-remember \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{"text": "#community: user reported bug in v1.2, fix shipped in v1.2.1.", "title": "discord-memory - note"}'

Static analysis

No suspicious patterns detected.