AI Social Media Manager

• Outcome: Review
• Latest audit: May 29, 2026 at 9:24 PM UTC
• Version:
  1.0.0

Overview

This social-media automation skill is purpose-related, but it asks users to put powerful social account credentials in a markdown file and under-explains the risks of automated posting and replies.

Review before installing. Do not put real passwords, session cookies, or production tokens in TOOLS.md; use scoped test accounts or a secret manager, and require manual approval before any post, reply, or bulk interaction.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README promotes automated comment replies and later instructs users to place sensitive platform credentials in TOOLS.md, but it does not warn about account-lockout, platform policy violations, accidental mass actions, or the risks of storing cookies/passwords/API tokens. In an agent skill context, this omission is security-relevant because users may enable high-impact automation with privileged credentials and underestimate the chance of abuse, leakage, or account suspension.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly advertises automatic replies to comments and private messages, which are outward-facing account actions, but it does not warn users that the tool may post or send messages on their behalf. In a social media management context, this can lead to unintended public communications, brand damage, spam-like behavior, or policy violations if users do not understand the automation scope.

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The documentation instructs users to place usernames, passwords, API keys, secrets, and cookies directly in TOOLS.md, which is an unsafe location for sensitive credentials. Storing secrets in documentation-like files increases the risk of accidental exposure through source control, sharing, logs, backups, or other tooling that reads project files.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The README explicitly documents automated posting, comment retrieval, and analytics actions against external social platforms but does not warn users that these operations can publish content, access account data, or trigger account-affecting actions. In an agent/skill context, omission of such warnings can lead to unintended external actions, abuse of connected accounts, or policy violations if users invoke the capability without informed consent.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The README shows credential configuration examples including cookies, passwords, API keys, and access tokens without any warning about secure secret storage or handling. This encourages unsafe practices such as placing secrets in documentation-managed files, increasing the risk of credential leakage, account takeover, and unauthorized API use.

VirusTotal

64/64 vendors flagged this skill as clean.