Security audit

biostartechnologylinkedin

Security checks for vulnerabilities and agentic risk

Overview

This is a LinkedIn content-writing helper with no executable code or privileged behavior; its broad activation wording is a usability note, not a security concern.

Installers should treat this as a writing-style helper for LinkedIn content. Review generated claims, metrics, client references, and hashtags before publishing, especially because the skill may use placeholders when proof is missing.

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

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description says to use the skill for creating LinkedIn posts "across any professional niche" and lists many generic content tasks without clearly delimiting trigger phrases or exclusion conditions. In a markdown skill description, this breadth can overlap with many ordinary writing requests and makes it unclear when the skill should or should not activate.
Content: No source excerpt is available for this finding.