Security audit

Linkedin Engager Analytics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkedIn audience-analysis workflow that uses Apify to fetch public post engagement and produce outreach-oriented reports, with privacy and scope cautions but no hidden execution or persistence.

Install only if you are comfortable using Apify to analyze LinkedIn engagement data. Keep runs limited to posts you own or have permission to analyze, review any outreach suggestions before using them, and watch Apify costs when increasing max engager counts.

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.
md
Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.
md
Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The phrase "audience analytics" is highly generic and can apply to many platforms, reports, or marketing tasks, so it may activate this skill outside its intended LinkedIn-specific use case. Because this skill performs audience segmentation and outreach-oriented analysis on public engager data, accidental activation could expose users to inappropriate data collection, cost-incurring API calls, and privacy-invasive recommendations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The phrase "audience analytics" is highly generic and can apply to many platforms, reports, or marketing tasks, so it may activate this skill outside its intended LinkedIn-specific use case. Because this skill performs audience segmentation and outreach-oriented analysis on public engager data, accidental activation could expose users to inappropriate data collection, cost-incurring API calls, and privacy-invasive recommendations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This markdown file includes an output category for "DM-able prospects" and a one-line opener seed, which implies generating direct-outreach recommendations. Under the markdown criteria, skills that can affect user privacy or external interactions should disclose such behavior, but no warning is present in this file about contacting real people or handling profile-derived data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.