Blotato Post Everywhere

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.1

Overview

This skill matches its stated social-posting purpose, but it tells agents to store a powerful posting API key in a plaintext workspace file.

Install only if you are comfortable giving the agent authority to publish or schedule real posts through your connected Blotato social accounts. Do not store the Blotato API key in TOOLS.md; provide it only at runtime or use a proper secret store. Before each run, manually verify the final text, target accounts/platforms, media files, and posting time.

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 (4)

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The skill explicitly instructs the agent to persist a user-provided Blotato API key into TOOLS.md, which creates unnecessary credential retention and expands exposure beyond the immediate task. Storing secrets in a local knowledge file can leak them to future prompts, logs, backups, or other skills, enabling unauthorized posting to all connected social accounts.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill is designed to publish and schedule posts across multiple external social platforms, but it does not prominently warn that execution will post publicly through the user's connected accounts. This can cause unintended publication, reputational harm, or accidental scheduling if the user does not fully understand the external side effects.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The script accepts arbitrary local file paths and uploads file contents to an external presigned URL, but the CLI help labels these as 'public media URLs' and does not clearly warn that local files will be transmitted off-host. In an agent skill context, this is more dangerous because a caller may believe they are only referencing media, while the code can exfiltrate local files if given sensitive paths.

Ssd 3

Medium

• Confidence: 97% confidence
• Finding: Directing the agent to save a user API key in a natural-language file creates a data retention risk because the secret may persist long after the task completes and become accessible in unrelated contexts. Even without malicious intent, this increases the chance of accidental disclosure through file inspection, prompt inclusion, syncing, or debugging workflows.

VirusTotal

67/67 vendors flagged this skill as clean.