ClawHub
Back to skill

Security audit

content-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is for external persistent content memory, but it tells agents to save interaction summaries automatically without clear user approval or retention controls.

Review this before installing if you handle private drafts, business ideas, client material, or personal data. Only use it where sending selected content to BlueColumn for persistent memory is acceptable, and prefer asking the agent to save specific items rather than letting it summarize and store every interaction automatically.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs agents to store and recall user content through BlueColumn persistent memory, but it does not require notice, consent, or clear disclosure that user-provided material will be transmitted to and retained by a third-party service. This creates a privacy and data-governance risk because users may unknowingly have drafts, ideas, or other sensitive content persisted outside the primary system.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill includes a direct example of sending content to an external endpoint with an authorization bearer token, which confirms third-party transmission of user content. External transmission is not inherently malicious, but here it is security-relevant because the skill does not pair it with safeguards around consent, data classification, or secret-handling guidance beyond reading the API key.

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": "Idea: 'Replace conversation history with semantic memory' — draft outline started 7/30.", "title": "content-memory - note"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow tells the agent to automatically store a summary after the interaction, which normalizes silent persistence of user-derived content without confirming that the user wants long-term storage. Automatic post-interaction saving increases the chance of capturing sensitive or unintended information and sending it to an external memory provider.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Persisting conversation summaries after every interaction creates an ongoing retention channel for natural-language user data, including potentially sensitive personal, business, or confidential information. In this skill's context, the danger is elevated because the retained content is specifically user ideas and drafts, which are often proprietary or private.

Content

No source excerpt is available for this finding.