ClawHub
Back to skill

Security audit

a-stock-stop-loss

Security checks for vulnerabilities and agentic risk

Overview

This is a small stop-loss trading guidance skill, but it gives direct sell-order style instructions without clear user confirmation, risk limits, or financial-advice boundaries.

Review this skill carefully before installing. It does not appear to contain code or technical persistence, but it may cause an agent to give firm trading instructions. Use it only as an informational framework, and do not allow trades or account actions without explicit human review and confirmation.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill gives concrete sell instructions, including 'unconditional stop-loss' and selling at next-day auction during extreme events, without any warning about market risk, slippage, liquidity, regulatory constraints, or whether the agent may execute trades autonomously. Because these recommendations can directly drive consequential financial actions, the absence of risk disclosures and execution safeguards materially increases the chance of harmful or unintended trades.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad, conversational, and likely to match ordinary investing questions such as whether to hold, stop out, or take profit. In a trading skill, unclear activation scope is dangerous because it can cause the agent to invoke prescriptive risk-management logic in situations where the user may only be asking for general discussion, increasing the chance of unintended financial guidance or action.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

All user-facing descriptive and trigger language in the file is Chinese, but the skill does not state that it is intentionally limited to Chinese-speaking users or A-share contexts as a documented locale choice. Under the policy, a language restriction should be justified or offered as a user opt-in rather than implicitly enforced.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.