Back to skill

Security audit

Smart Commit

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only helper for writing commit, PR, and release-note text, and its git-diff guidance fits that purpose.

Install this only if you want your agent to inspect provided diffs or read local git history for commit, PR, or release-note drafting. Be aware that repository diffs can contain private code or secrets, so use explicit prompts and override the language choice when needed.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README defines very broad activation examples such as generic requests about commit messages, PR descriptions, changelogs, and impact analysis. In an agentic environment, overly broad trigger phrases can cause the skill to activate during ordinary conversation or on unrelated repository content, increasing the chance that sensitive diffs, internal text, or user intent are processed unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The keyword-based trigger rule matches terms like 'commit', '提交', 'PR描述', 'changelog', and '发布说明' without requiring surrounding context that confirms the user wants this skill executed. This can lead to accidental activation during casual discussion, code review, or documentation tasks, causing the agent to steer into git-analysis behavior unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill’s activation guidance includes broad, everyday requests such as wanting git history to be 'more规范' or asking to analyze change impact. In an agentic environment, vague triggers can cause the skill to be invoked when the user did not explicitly ask for commit/PR/release-note generation, increasing the chance of inappropriate context collection or unnecessary git-diff analysis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The rule hard-codes language-specific output preferences such as forcing English for Go, Python, TS/JS, and Rust projects, without saying this should defer to explicit user preference or repository policy. In a commit-generation skill, this can cause the agent to ignore the user's requested language and produce misleading or unusable project metadata, especially in Chinese-speaking or mixed-language teams.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Lines L176-L183 explicitly specify that the expected output is a Chinese commit message. This imposes a language requirement without indicating user opt-in or explaining that the skill is limited to a Chinese-only or region-specific context, which matches the locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The phrase “中英文自适应 — 根据项目语言自动选择” indicates the skill may force output language based on project context rather than user preference. This can conflict with language/locale policy expectations when no user opt-in or override is described.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

L161-L164 指示“根据项目语言自动判断”提交信息语言,仅在用户明确要求时才跟随用户,这会在无显式同意下对语言/locale 做默认决定。按规则,强制或预设特定语言而缺少明确用户 opt-in 可能构成自然语言策略问题。

Content

No source excerpt is available for this finding.