Security audit

gist-post

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper for publishing user-chosen content to GitHub Gist, with real privacy cautions but no hidden or deceptive behavior found.

Install only if you intend agents to publish selected content to GitHub Gist. Use a token limited to the gist scope, avoid storing or pasting real tokens into prompts or shared files, and review every Gist for secrets, personal data, private logs, proprietary code, and internal context before posting. Prefer --secret for non-indexed sharing, but remember anyone with the URL can still access it.

SkillSpector

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 (3)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README explicitly instructs users to create public gists and emphasizes that they are readable by anyone, but it does not clearly warn against posting secrets, credentials, internal prompts, or other sensitive context. In an agent skill whose purpose is to share rich context, this omission is risky because users may unintentionally exfiltrate private or regulated data to a world-readable URL.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill explicitly encourages posting 'any content' and broad classes of data such as reports, logs, and handoff context without defining approval gates, data classification checks, or safe-use boundaries. In an agent setting, this can lead to accidental exfiltration of sensitive internal context to an external service because the default behavior is framed as a generally useful publishing mechanism rather than a narrowly scoped action.

Missing User Warnings

High

Confidence: 97% confidence
Finding: The skill promotes public GitHub Gists as a normal sharing mechanism and highlights that they are readable by anyone, but it does not give a strong warning that posting may permanently expose sensitive or regulated information to a third party. Because the skill is designed for sharing rich context between agents and humans, the surrounding context makes accidental disclosure more likely and more dangerous than a generic documentation example.

Static analysis

No suspicious patterns detected.