Security audit

git-weekly

Security checks for vulnerabilities and agentic risk

Overview

This skill has a legitimate Git weekly-report purpose, but it can automatically read full recent code changes after a broad summary trigger.

Review this skill before installing if you work in private or sensitive repositories. Prefer invoking it explicitly with git-weekly, and consider adding a confirmation step or using git log summaries before allowing full patch analysis.

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
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: 97% confidence
Finding: The skill instructs automatic execution of `git log --since="7 days ago" --author="$(git config user.name)" --reverse --patch`, which exposes full patch contents without a prior warning or consent gate. Patch output can contain sensitive source code, secrets, internal URLs, credentials, or proprietary business logic, so automatic collection materially increases data-exposure risk. The surrounding skill context makes this more dangerous because the stated behavior is to run immediately when triggered.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases include very generic user inputs such as “生成总结”, which can easily match ordinary requests unrelated to this skill. That increases the chance of accidental activation and unintended execution of the workflow, including repository inspection steps the user did not explicitly request. In this skill’s context, broad triggering is more dangerous because activation leads directly to collecting and analyzing git history and patches.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The natural-language description, role, instructions, output format, and trigger phrases are all written to require Chinese output and interaction, but the file does not provide any user opt-in or alternative language option. This can violate language/locale policy when a skill forces a specific language by default.

Static analysis

No suspicious patterns detected.