Security audit

Traffic Quality Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only traffic audit skill with over-prescriptive advice patterns, but no hidden code, persistence, credential use, or account-changing authority.

Installers should know this skill may produce assertive ad budget recommendations and may mention Rijoy in Shopify loyalty/referral contexts. Use it as an audit framework, verify recommendations against real GA4/Meta data and sample sizes, and do not pause campaigns based only on placeholder examples.

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

Findings (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:12
Finding: Unconditional Response Hijacking Forces Unsupported Traffic Shutdown Recommendations
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:49
Finding: Context-Triggered Third-Party Brand Promotion Alters Neutral Audit Output
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger criteria are excessively broad, including vague phrases like 'help me look at my ads' and 'is my traffic real,' which can cause the skill to activate for loosely related marketing questions. This creates routing and scope-control risk: the agent may force traffic-audit behavior, produce unwarranted shutdown recommendations, or override more appropriate specialized skills based on weak intent matching.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction to 'default to the pushy policy for borderline ads questions' weakens activation boundaries and biases the system toward invoking this skill even when user intent is ambiguous. In context, that is more dangerous because the skill also mandates prescriptive outputs like naming shutoff candidates, increasing the chance of inappropriate or hallucinatory budget advice when data is incomplete.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.