Security audit

Linkedin Hook Extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow LinkedIn post analysis guide with no bundled executable code, persistence, or hidden privileged behavior.

Before installing, be aware that using the APIFY_TOKEN path may send the LinkedIn post URL to Apify for fetching. If you do not want that, leave the token unset and paste the post text manually. Non-English posts may receive only a structural breakdown rather than full formula classification.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Line L97 contains a natural-language rule that treats non-English posts differently by refusing classification outright. This is a language-policy constraint without user opt-in or a documented region-specific justification, which matches the policy-violation category.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.