gitee

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Gitee helper skill whose repository read and write capabilities are disclosed and aligned with its stated purpose.

Install only if you want an agent to help with Gitee API and git workflows. Use a least-privilege Gitee token, limit it to the repositories and actions needed, and require explicit confirmation before issue creation, pull request creation, file updates, or any git push.

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)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill explicitly instructs users to create or update repository contents on the remote service but does not warn that this modifies live remote data. In an agent context, omission of a write-safety warning increases the risk of unintended repository changes, especially if the agent is asked to inspect rather than mutate state.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documented push commands publish local commits to a remote Gitee repository, but the skill does not clearly warn that these actions are externally visible and can alter shared project state. In an agent skill, this can lead to accidental disclosure or unauthorized publication of local work if the agent follows the examples mechanically.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal