Security audit

Alpha Pulse 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China A-share market scanner, with some ordinary setup and notification risks users should review before use.

Install it in a virtual environment, pin or review dependency versions before running pip, avoid placing sensitive tokens in shared workspaces, and turn off clipboard, voice, popup, or auto-open report behavior unless you specifically want those local side effects.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:42
Finding: Unpinned and Unverified Third-Party Dependencies
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The notify capability advertises Windows popups, clipboard access, and voice output without any user-facing warning or consent model. These behaviors can leak sensitive information to the screen, alter the user’s clipboard unexpectedly, or cause disruptive audio output, especially if the skill is triggered unintentionally or handles sensitive trading data.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrase is overly permissive because a natural-language utterance like “alpha-pulse predict” can invoke the skill without an explicit confirmation boundary. In this skill’s context, invocation can lead to downstream actions such as generating reports, opening files, or preparing local artifacts, so accidental or prompt-injected activation is a real safety risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill states it will immediately create config.yaml and lib/scanner.py skeletons, but does not clearly warn users that local files may be created automatically. Silent filesystem writes are dangerous because they can surprise users, overwrite existing content, or be abused through unintended activation to modify the local environment.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code file contains natural-language descriptions entirely in Chinese and presents the skill as an A-share market scanner without any opt-in or alternative language support. Under the stated policy, forcing a specific language or locale without user choice is a natural-language policy violation unless clearly documented as a justified regional tool.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The function docstrings, comments, and example usage are written in Chinese only, which effectively constrains the skill's operational language for readers and users. The policy allows locale constraints only when they are clearly documented and justified or when users are given a choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The entire skill description, commands guidance, and response instructions are written to require Chinese interaction, including the explicit reply format 继续 or custom [需求]. There is no indication that users may choose another language or locale, which can violate language-choice policy when not justified or offered as opt-in.
Content: No source excerpt is available for this finding.