Back to skill

Security audit

gist-post

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it defaults agents toward publishing arbitrary content to a public GitHub Gist without a required sensitive-data check or confirmation step.

Review this skill carefully before installing. Use it only for content you have intentionally reviewed for public sharing, prefer secret Gists for non-public material, and never include tokens, credentials, private logs, customer data, or internal context. Store the GitHub token with the least necessary scope and rotate it if it may have been exposed.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:34
Finding

Public Gist Publication Is the Default Without a Sensitive-Data Review

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 36)May include surrounding context.

git clone https://github.com/PsiClawOps/gist-share ~/.openclaw/skills/gist-share

text

### 2. Create a GitHub Personal Access Token (PAT)

1. Go to [github.com/settings/tokens](https://github.com/settings/tokens)
2. Click **"Generate new token (classic)"**

Credential Access

High
Category
Privilege Escalation
Confidence
79% confidence
Finding

The skill requires a GitHub Personal Access Token in the environment, which is a legitimate operational need, but it normalizes credential setup without any handling guidance, least-privilege notes beyond the scope name, or warnings about leaking the token through command output, logs, or downstream gist content. In an agent context, environment-provided secrets are especially sensitive because other tools or prompts may inadvertently expose them.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
## Setup

You need a GitHub Personal Access Token scoped to `gist`, set as `GITHUB_TOKEN` in your environment. Ask your agent to walk you through creating one if you haven't already.

---

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 36)May include surrounding context.

git clone https://github.com/PsiClawOps/gist-share ~/.openclaw/skills/gist-share

text

### 2. Create a GitHub Personal Access Token (PAT)

1. Go to [github.com/settings/tokens](https://github.com/settings/tokens)
2. Click **"Generate new token (classic)"**

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README explicitly instructs the agent to create a public GitHub Gist and emphasizes that it is readable by anyone, but it does not provide a prominent warning against posting secrets, credentials, personal data, or internal context. In an agent skill, this is risky because users may hand off arbitrary runtime context, and the default example encourages publication to a world-readable URL.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly encourages posting arbitrary content to a public GitHub Gist and emphasizes that it is readable by anyone, but it does not provide a prominent warning against publishing sensitive data such as credentials, internal reports, logs, or user information. In an agent setting, this increases the risk of accidental data exfiltration because operators may treat the skill as a general-purpose sharing mechanism without understanding the permanence and public exposure of the output.

Content

No source excerpt is available for this finding.