Security audit

github-open-source-project-polish

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for open-source project setup, but it defaults to creating and pushing to a public GitHub repository without a clear final confirmation step.

Install only if you want the agent to prepare projects for public open-source release. Before allowing any GitHub action, require an explicit confirmation of the account, repository name, public visibility, branch/ref being pushed, and results of a full secret and history review; otherwise use it only for local documentation polishing.

A.I.G

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

Error

Location: SKILL.md:22
Finding: Unattended Public GitHub Publication May Expose Sensitive Repository Content and History
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly defaults to creating a public GitHub remote and pushing changes for projects without an existing remote, but it does not require an explicit, user-facing confirmation immediately before publication. This creates a real risk of unintentionally exposing proprietary code, embedded secrets, internal documentation, or sensitive repository metadata through irreversible public release.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The recommended CLI flow uses gh repo create ... --public --source=. --remote=origin --push, which can immediately publish the current repository contents to a public GitHub repository. Even though the skill mentions secret checks elsewhere, the workflow lacks a mandatory explicit warning/confirmation gate tied to the actual publication command, making accidental public disclosure more likely.
Content: No source excerpt is available for this finding.