Security audit

Linkedin Post Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only LinkedIn draft review checklist with no executable code, credentials, persistence, or posting authority.

Install only if you want opinionated LinkedIn optimization and AI-tell cleanup. Treat its algorithm and AI-detection scores as heuristic writing advice, not guaranteed platform or detector results, and review any suggested rewrite before using it publicly.

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 (3)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.
md
- `SKILL.md` — this file

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The description hard-codes LinkedIn-specific "2026 algorithm heuristics and voice rules" as the governing standard, which can impose a platform-specific communication norm without any user opt-in or stated justification. This reads as a fixed policy constraint rather than a configurable preference.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill declares that it is auto-invoked when linkedin-post-writer finishes a draft, but it does not define explicit gating conditions, user consent, or boundaries for when that chaining should occur. Ambiguous auto-invocation can cause unintended execution on user content, surprise data flow between skills, and policy bypass if downstream actions occur without a clear trigger contract.
Content: No source excerpt is available for this finding.