Security audit

Phy Social Post

Security checks across malware telemetry and agentic risk

Overview

This skill is meant for social posting, but it gives an agent live posting workflows through API keys without a clear final approval safeguard.

Install only if you intend to let an agent help publish through your social media accounts. Before using it, verify the separate local social-posting-api code, keep only the required provider keys in its .env file, and require a manual final review of the post text, media, platforms, connected accounts, and schedule before any command is run.

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger condition includes broad language such as any social posting request, which can cause the skill to activate in situations where the user did not clearly intend to publish content. In a skill that performs external side effects against connected social accounts, overbroad activation materially increases the risk of accidental posting to public platforms.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill presents executable posting examples and workflow steps without a prominent warning that running them will publish to real, connected social media accounts. Because the action is externally visible and potentially irreversible, lack of disclosure can lead to accidental public posts, reputational damage, and unintended business communications.

VirusTotal

No VirusTotal findings

View on VirusTotal

Static analysis

No suspicious patterns detected.