ClawHub
Back to skill

Security audit

Building with MemorySync

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for integrating MemorySync, and its external API and memory-storage behavior are disclosed and aligned with that purpose.

Install this only if you intend to build with MemorySync and are comfortable sending selected user facts or conversation turns to that external service. Review its current docs and privacy terms, avoid storing secrets or sensitive identifiers, and keep user-scoping headers under your control.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 161)May include surrounding context.

md
## 6. Hard invariants (do not violate)

- **Never call `DELETE /memory/user/purge`.** Despite the path, it erases the
  ENTIRE ACCOUNT behind the credential — keys, memberships, everything. It
  ignores `X-End-User-ID`. Delete individual memories by id via
  `DELETE /memory/forget` with `memory_ids`.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
- **Never call `DELETE /memory/user/purge`.** Despite the path, it erases the
  ENTIRE ACCOUNT behind the credential — keys, memberships, everything. It
  ignores `X-End-User-ID`. Delete individual memories by id via
  `DELETE /memory/forget` with `memory_ids`.
- Anything that runs inside a user's session (hooks, middleware) must
  fail open: a memory outage is a memoryless turn, never a broken app.
- Keep `X-End-User-ID` out of logs if your users' ids are sensitive; never

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
85% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: building-with-memorysync
description: Guide for building, reviewing, evaluating, and troubleshooting applications that use MemorySync — the memory platform with verbatim conversation history plus server-side distilled facts, header-enforced end-user isolation, and silent quota degradation in production. Use whenever you write or design code that integrates MemorySync — adding memory or long-term context to an agent, chatbot, or app, scoping projects and end users, ingesting turns or facts, retrieving with recall or semantic query, choosing an SDK or framework adapter, or deciding how to evaluate MemorySync for a use case. Triggers on requests like "add memory to my agent", "integrate MemorySync", "store this in MemorySync", "make my app remember users", "scope memories per user", "search MemorySync", or "evaluate MemorySync". Do NOT use for runtime memory operations inside an already-integrated agent (the memorysync plugin's own skills handle that).
license: MIT
metadata:
  author: memorysync

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 115)May include surrounding context.

md
MemorySync is the one platform where YOU (the coding agent) can provision a
working key with no human in the loop:

1. **Mint**: `POST https://api.memorysync.io/evaluation/keys` — body optional
   (`{"agent_caller": "claude-code"}`). A `201` returns `api_key`,
   `default_user_id`, `project_id`, `mcp_url`, `expires_at`, `limits`
   (add/retrieval/storage), and a `claim_command`. A `429` means the per-IP

Static analysis

No suspicious patterns detected.