ClawHub
Back to skill

Security audit

Openclawdy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed external memory service for agents, with expected persistence and sharing features that users should configure carefully.

Install only if you want an external hosted service to retain agent memory. Treat stored memories and pool IDs as sensitive, avoid storing secrets or credentials, review what agents can write to shared pools, and be careful with vault clear or snapshot overwrite because they can remove or replace memory state.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Content
Delete a specific memory by ID.

**Endpoint:** `DELETE /api/memory/{id}`

**Parameters:**
- `id` (required): The memory ID to delete
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).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
Clear all memories in the vault. **Use with caution - this is irreversible.**

**Endpoint:** `DELETE /api/memory/vault`

---
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).

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill promotes cross-agent memory pools but does not plainly warn that any data written to a pool is shared with other agents that know or are granted the pool identifier. In a memory product, agents may store sensitive prompts, user data, or operational context, so underemphasizing the shared-visibility model can lead to accidental data disclosure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The snapshot restore feature includes an overwrite mode but does not prominently warn that it can replace the current memory state and potentially destroy newer data or corrupt an agent's working context. For autonomous agents relying on memory for decisions, accidental restore-overwrite can cause loss of integrity, rollback to unsafe state, or irreversible operational mistakes.

Static analysis

No suspicious patterns detected.