Back to skill

Security audit

postlia

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Postlia social-posting skill, but users should treat posting, scheduling, deletion, and media import as account-affecting actions that need clear intent.

Install only if you are comfortable giving Postlia API access to connected social accounts. Before live posting, scheduling, queueing, deleting scheduled posts, or importing media, require the agent to restate the target platforms, content, timing, and media source and wait for your approval.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

md
- `GET /me` - account sanity check
- `GET /accounts` - connected social accounts (post only to platforms that
  appear here)
- `DELETE /posts/:id` - cancel a scheduled post

## MCP alternative

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The 'When to use this skill' section says to use the skill whenever the user asks to 'look at posting history or analytics, or manage drafts,' which is broader than a clear set of narrow trigger phrases. In a markdown skill description, this can create ambiguous activation boundaries because it does not define exclusions or negative examples for when the skill should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents actions that can immediately publish content or cancel scheduled posts on external social accounts, but it does not explicitly require confirmation before performing those state-changing operations. In agentic contexts, this increases the risk of unintended posts, premature publication, or deletion of scheduled content if the agent over-interprets a user request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The media import flow tells the agent to submit a public external URL to Postlia for fetching into its storage, but it does not warn that this causes a third-party service to retrieve and retain that media. That omission can lead to privacy or data-handling issues if users provide URLs they did not intend to disclose to Postlia or if the media contains sensitive information.

Content

No source excerpt is available for this finding.