Back to skill

Security audit

友行

Security checks for vulnerabilities and agentic risk

Overview

The skill is a purpose-aligned event lookup tool, but it uses unsafe shell-based instructions for user-provided activity IDs and has broad activation plus third-party API calls that need review.

Review before installing. The event lookup behavior itself is coherent, but the skill should narrow activation to explicit activity queries, clearly disclose that it contacts api.cumen.fun, and replace the node -e placeholder pattern with validated campaign IDs passed as safe process arguments or handled by a scoped HTTP tool.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:91
Finding

Command Injection Through Unsafe Campaign ID Substitution

Content
View full analysis
Remediation
View remediation
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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation criteria are overly broad because the skill can trigger on a mere mention of “友行” or “友行青年社群” without confirming the user is asking about events. That can cause unintended tool use and unnecessary disclosure of user prompts or query parameters to the external service, especially in conversations where the entity is mentioned incidentally.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

text
CLUB_ID = 018c32aa-7958-ede5-c6ae-403c9881a2a5
API_BASE = https://api.cumen.fun/api/xx.cumen.v1.CumenService

功能一:列出所有活动

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill performs external API requests but does not disclose that user-driven queries will be sent to a third-party domain. This creates a transparency and privacy risk because users may unknowingly cause conversation-derived data, such as requested campaign IDs or event lookups, to be transmitted outside the host system.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This code actively sends POST requests to a third-party service to retrieve club campaign data. In context, the danger is not the network call itself but that it can be invoked under broad triggers and without any user notice, leading to unintended external transmission of request data and metadata.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

bash
node -e "
const https = require('https');
const API = 'https://api.cumen.fun/api/xx.cumen.v1.CumenService/ListCampaignsOfClub';
const CLUB_ID = '018c32aa-7958-ede5-c6ae-403c9881a2a5';

function post(url, body) {

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This code sends a campaign ID to an external service to fetch event details. While functionally aligned with the skill’s purpose, it still creates an external transmission path that can expose user-request-derived identifiers or usage patterns if invoked without clear intent and transparency.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

bash
node -e "
const https = require('https');
const API = 'https://api.cumen.fun/api/xx.cumen.v1.CumenService/GetCampaign';
const CAMPAIGN_ID = 'CAMPAIGN_ID';

function post(url, body) {