Security audit

Linkedin Post Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent LinkedIn post drafting and publishing workflow, with the main risk being that users should confirm before anything is posted or scheduled publicly.

Before installing, understand that this skill can help publish or schedule real LinkedIn posts through the configured publishing wrapper after approval. Confirm the exact LinkedIn account, final post text, media, and scheduled time before approving publication.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.
md
Global voice rules: see root `SKILL.md` §Voice rules. Additional skill-specific rules:

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill includes a concrete publishing action to LinkedIn via lib.publish(...) after approval, but it does not require an explicit user-facing confirmation warning that content may be posted or scheduled to a real external account. In an agent setting, ambiguous 'approval' handling can lead to unintended publication, reputational harm, or accidental scheduling to the wrong profile if the user does not clearly understand that an external side effect will occur.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: These instructions prescribe rigid stylistic rules such as banning em dashes, curly quotes, and Oxford commas, which are language/locale-dependent writing conventions. Because the file presents them as mandatory requirements rather than optional preferences, it can violate policy against forcing a specific language or locale style without user choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.