Security audit

Multi-Platform Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly described social-media posting helper, with expected account access and publishing side effects disclosed, but users should treat publishing and account authorization carefully.

Before installing, confirm you are comfortable granting access to each social account, use the narrowest available OAuth/API scopes, avoid pasting secrets into normal chat, and review every confirmation screen carefully because published or scheduled posts may not be fully reversible across all platforms.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README encourages one-click and scheduled posting across multiple external platforms but does not warn users about irreversible or partially reversible actions, per-platform failures, or rollback limitations. In this context, users may unintentionally publish content broadly, encounter inconsistent post states across platforms, or assume that a single rollback action will reliably undo all changes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill asks users to bind multiple platform accounts and describes analytics collection, but it does not document how credentials are stored, protected, refreshed, or what data is collected and retained. Because this skill centralizes access to several social accounts, unclear credential and privacy handling increases the risk of account compromise, overbroad access, and unintended exposure of performance or content data.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The natural-language instructions, examples, and outputs are all presented in Chinese, which effectively forces a single language experience. There is no indication that the skill supports user language preference, offers opt-in language selection, or is intentionally limited to a Chinese-only region-specific deployment.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad, generic, and overlap with ordinary user requests about posting or distributing content, which can cause the skill to activate outside a clearly intended scope. In a skill that can publish content across multiple social platforms, unintended activation increases the risk of accidental posting workflows, confused delegation, or unsafe handling of user content and connected platform credentials.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The README forces a single language presentation throughout and does not indicate that users may select another language or that the skill is intentionally limited to a Chinese-language audience. Under the stated policy, fixed language behavior without user opt-in can be a natural-language policy concern unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.