ClawHub
Back to skill

Security audit

postlia

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed social posting integration, but users should treat publishing, scheduling, and canceling posts as real account actions that need explicit review.

Install this only if you want an agent to use your Postlia API key for real social media workflows. Before any publish, schedule, queue, media upload, MCP connection, or scheduled-post cancellation, confirm the exact content, platforms, account, time, and post ID.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation guidance is broad enough to invoke this skill for general requests about social media, history, analytics, or drafts, not just explicit user intent to publish. Because this skill can perform live external actions against connected accounts, over-broad triggering increases the risk of unintended posting, scheduling, or account-affecting operations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation does not prominently warn that it can publish real content to external social platforms using the user's connected accounts. In an agent setting, this omission can cause users or orchestrators to treat the skill as informational rather than action-taking, increasing the likelihood of accidental public posts with reputational or business impact.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The documented delete operation cancels scheduled posts, which is a destructive action, but the skill gives no caution about confirming intent or verifying the target post ID. In an autonomous or loosely supervised agent flow, this can lead to accidental cancellation of legitimate scheduled content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.