ClawHub
Back to skill

Security audit

Alphagbm Investment Thesis

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for tracking investment theses, but it exposes permanent deletion of financial research records without clear confirmation safeguards.

Review this skill before installing if you keep important investment notes in AlphaGBM. It should only be used with an API key you intend to grant access to your thesis records, and deletion should be treated as permanent unless the service separately provides recovery or server-side safeguards.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
### 5. Delete thesis (by id)

```
DELETE /api/research/theses/<THESIS_ID>
```

Hard-delete. Also uses numeric id.
Confidence
94% confidence
Finding
The skill exposes a destructive DELETE endpoint that accepts only a numeric thesis ID, with no documented guardrails such as ownership verification, confirmation, or constraints on how the ID is sourced. In an agentic context, this creates tool-parameter abuse risk: a mistaken, guessed, stale, or adversarially supplied ID could cause unauthorized or unintended deletion of records.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase "update my thesis" is overly broad and can match ordinary conversation without clearly signaling intent to invoke this skill. In an agent environment, broad activation increases the chance of unintended tool use that can modify investment records or initiate follow-on API actions without sufficiently explicit user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents irreversible hard-delete behavior but does not instruct the agent to warn the user, confirm intent, or offer safer alternatives like close/archive. In a conversational workflow, that omission can lead to accidental permanent loss of thesis records from ambiguous or misinterpreted requests.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The trigger list includes Chinese phrases alongside English ones, but the skill does not explain whether multilingual behavior is optional, user-driven, or limited to a specific locale. This can create ambiguity around language handling and may violate language-choice expectations if the skill is assumed to operate under a single default language policy.

Static analysis

No suspicious patterns detected.