ClawHub
Back to skill

Security audit

Gitea

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Gitea CLI reference skill with some powerful manual commands that users should run carefully.

Install only if you intend to let the agent help operate Gitea through your tea CLI account. Review destructive or sensitive commands before running them, especially repository deletion, action secrets, variables, comments, releases, and webhooks.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This markdown file includes a force-delete command for a repository, but it does not warn the user that the action is destructive and potentially irreversible. Under the markdown-specific warning criteria, commands that can affect user data or system integrity should be accompanied by a clear caution.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill describes listing and creating action secrets, which involves handling sensitive credentials, but it provides no warning about securely entering, storing, or auditing secret values. Markdown skill descriptions should warn about behaviors that may affect privacy or credential safety.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
Creating a webhook can send repository event data to a third-party endpoint, which has privacy and integrity implications, but the markdown provides no disclosure of that behavior. This is a user-impacting network/data-transmission action that should be explicitly warned about in the skill description.

Static analysis

No suspicious patterns detected.