ClawHub
Back to skill

Security audit

Mermail xStocks Desk

Security checks for vulnerabilities and agentic risk

Overview

This skill discloses a high-impact but tightly scoped xStocks DCA and email workflow that depends on user standing grants, previews, and approvals.

Install only if you want an agent to help manage approved xStocks DCA activity and related emails. Before use, define the budget, cadence, exact Solana mint allowlist, invoice recipients, and wallet carefully, and review every trading or email preview before approval.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The weekly statement is specified as a 'weekly statement draft' with CSV, and the surrounding document consistently prescribes fixed output conventions and English example phrasing without any opt-in for language or locale. For a user-facing email/reporting skill, this creates a language-policy concern because the skill does not offer a language choice or document a justified locale restriction.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The default prompt is broadly phrased to 'run my standing xStocks grant' under 'exact authorization' without encoding concrete trigger boundaries, confirmation requirements, or narrow execution conditions. In a trading and email-automation context tied to a standing grant, this can cause the agent to over-apply the skill in ambiguous situations and initiate asset purchases or send transactional emails when the user did not intend to invoke this desk workflow.

Static analysis

No suspicious patterns detected.