Security audit

AnalyticLunch

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with AnalyticLunch analytics use, but it asks the agent to run raw curl commands with an API key and includes a state-changing tracking-link action without enough guardrails.

Review this skill before installing if your AnalyticLunch API key has broad account access. Use it only for sites and reports you are authorized to access, and be cautious with tracking-link creation because it changes account data. Prefer an implementation that sends structured HTTP requests and JSON-serializes user input instead of interpolating values into shell commands.

A.I.G

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:64
Finding: Potential Shell Command Injection Through Unsafe Tracking-Link Parameters
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill describes querying traffic data, tracking links, and reports but does not clearly warn that user requests will send analytics-related identifiers and queries to an external third-party service. This creates a transparency and privacy issue because users may not realize that their website intelligence requests are being transmitted off-platform.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 86% confidence
Finding: The skill explicitly instructs the agent to use curl with an API key to transmit requests to analyticlunch.com, which is a genuine external data transmission path. While external API use is expected for this functionality, it still represents a security-relevant capability because it can send sensitive analytics, site identifiers, and link-management actions to a third-party endpoint if invoked too broadly or without adequate user understanding.
Content: Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.
Example:

bash
curl -s -H "x-api-key: $ANALYTICLUNCH_API_KEY" "https://analyticlunch.com/api/traffic/sites"

Example with POST:

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases are broad enough to match common requests like 'how's traffic' or 'how's my website doing' without clearly constraining that the skill should only be used for the user's own AnalyticLunch account data. In an agent environment, this can cause over-invocation of the skill and unintended disclosure or retrieval of third-party analytics and competitive intelligence data from an external service.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.