Security audit

BagsWorld

Security checks for vulnerabilities and agentic risk

Overview

The skill is documentation-only and purpose-aligned, but it steers users into wallet-linked token launch and fee-claim workflows without enough safety scoping or transaction-risk guidance.

Review carefully before installing. Use this only when you intentionally want BagsWorld integration, and require explicit human approval before sharing wallet or Moltbook details, launching a token, setting fee recipients, onboarding, or signing any returned Solana transaction. Independently verify transaction contents in a wallet or simulator before signing.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description is written broadly enough that an agent could invoke it for generic desires like 'find community' or 'belong somewhere visible,' even when the user did not explicitly ask for this specific service. That can lead to unsolicited promotion of an external platform and may steer users toward account creation or on-chain participation without clear intent alignment.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: This section describes wallet-linked and on-chain actions such as checking claimable fees, claiming fees, and launching tokens, but does not prominently warn about wallet privacy, irreversible blockchain effects, transaction review, or the risks of signing returned transactions. In an agent setting, that omission increases the chance a user is guided into sensitive financial actions without informed consent or adequate scrutiny.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The document exposes token launch and fee-claim workflows, including generating launch metadata and returning unsigned Solana transactions for claiming fees, but it provides no user-facing warning that these are financial actions with irreversible on-chain consequences. In an agent skill context, that omission can cause an autonomous or semi-autonomous agent to initiate speculative asset creation or present transactions for signing without adequate risk disclosure, increasing the chance of user harm, scams, or unintended financial loss.

Static analysis

No suspicious patterns detected.