Social Insights

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 7:20 AM UTC
• Version: 1.3.0

Overview

This is a disclosed social media analytics skill with optional social API credentials, and the inspected artifacts do not show hidden execution, exfiltration, or destructive behavior.

Install only if you are comfortable providing social-platform credentials to the runtime. Prefer read-only, least-privilege tokens; keep business metrics and generated reports private; use manual CSV mode if you do not want to connect accounts. Treat automatic reporting claims as not implemented by the inspected script.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Credential Access

High

• Category: Privilege Escalation

Content

description: Twitter API Secret
          required: false
        LINKEDIN_ACCESS_TOKEN:
          description: LinkedIn Access Token
          required: false
        THREADS_TOKEN:
          description: Threads API Token

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 82% confidence
• Finding: The skill declares environment-variable requirements for multiple social-platform credentials but does not define any explicit permission or allowed-tools scope. That makes credential and data access boundaries unclear to users and the host platform, increasing the chance the skill can access sensitive secrets or analytics data without sufficiently transparent authorization expectations.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation example "When should I post for maximum engagement?" is a natural-language phrase that could easily occur in ordinary conversation and does not name the skill or narrow the context. The README does not provide exclusion conditions or a constrained activation scope, so this increases the risk of unintended invocation.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill requests or relies on social-platform credentials and analyzes potentially sensitive account-performance data, yet it does not present a clear warning about handling tokens, account metadata, competitor analysis data, and generated reports. Users may provide secrets or business-sensitive metrics without understanding the privacy implications or where the data may be processed.

Natural-Language Policy Violations

Low

• Confidence: 94% confidence
• Finding: Most of the skill is written in English, but the author-support section switches to Chinese without indicating that multilingual output is optional or user-selected. This can violate language/locale consistency expectations because the file imposes a different language in part of the user-facing documentation without opt-in.

Static analysis

No suspicious patterns detected.