Back to skill

Security audit

Referral Codes & Referrals Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple referral-code lookup that uses a disclosed public API and does not include local code execution, persistence, credential access, or hidden behavior.

Before installing, understand that referral lookups send the brand or domain you ask about to ReferralCodes.com and may return third-party referral links or codes. Avoid using it for confidential vendor research or internal project names unless that disclosure is acceptable.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

md
---

## Output rules

### If referrals are found:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The activation guidance includes broad phrases like "signup offers," "new user sign-up extras," and "app download incentives," which can overlap with ordinary discount or promotion requests not specifically about referrals. The file does not provide negative examples or boundaries clarifying when the skill should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill sends a user-derived brand or domain to an external public API without clearly warning the user. Even if the payload is usually low sensitivity, user queries can contain sensitive business interests, internal project names, or private vendor research, and the silent transfer violates transparency and can create privacy/compliance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.