Back to skill

Security audit

Openclaw Cc Rules Gitee

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed coding-workflow skill that adds planning, task tracking, and conservative Git rules, with no evidence of hidden execution, credential use, exfiltration, or destructive behavior.

Install this if you want OpenClaw to apply a structured coding workflow automatically during programming tasks. Expect broader activation across coding conversations and extra planning or confirmation steps. The README contains questionable provenance language, so install only if you trust the publisher/source.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (14)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README describes the skill as automatically invoking for essentially any programming-related content, which is overly broad for a persistent agent behavior. In a coding assistant context, this can cause unbounded activation across ordinary conversations, unexpectedly steering agent behavior and increasing the chance that the skill interferes with unrelated tasks or applies risky workflow instructions without explicit user intent.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
70% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 78)May include surrounding context.

md
### 🛡️ Git 安全协议 — 不作死

**绝对禁止(除非你明确要求):**
- `git push --force`
- `git reset --hard`
- `git checkout .` / `git restore .`
- `--no-verify` / `--no-gpg-sign`

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
70% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.

md
### 🛡️ Git 安全协议 — 不作死

**绝对禁止(除非你明确要求):**
- `git push --force`
- `git reset --hard`
- `git checkout .` / `git restore .`
- `--no-verify` / `--no-gpg-sign`

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 79)May include surrounding context.

md
**绝对禁止(除非你明确要求):**
- `git push --force`
- `git reset --hard`
- `git checkout .` / `git restore .`
- `--no-verify` / `--no-gpg-sign`
- `git commit --amend`(除非你说"修改上次 commit")

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

md
**绝对禁止(除非你明确要求):**
- `git push --force`
- `git reset --hard`
- `git checkout .` / `git restore .`
- `--no-verify` / `--no-gpg-sign`
- `git commit --amend`(除非你说"修改上次 commit")

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 176)May include surrounding context.

md
2. 分析变更:
   - 概括改动性质(新功能 / 增强 / 修复 / 重构 / 测试 / 文档)
   - 排除含敏感信息的文件(.env、credentials.json 等)
   - 写 1-2 句 commit message,聚焦"为什么改"而不是"改了什么"

3. 执行提交:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation trigger is described broadly as applying whenever OpenClaw 'detects a coding scenario,' without clear scoping, user confirmation, or explicit boundaries. Overbroad activation can cause the skill to engage in unintended contexts, influencing agent behavior more widely than expected and potentially interfering with safer higher-priority workflows or user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The phrase 'programming-related scenarios' is ambiguous and insufficiently bounded, making activation criteria hard to predict and easy to trigger accidentally. For a persistent skill, ambiguous triggering increases the risk of prompt-scope takeover, where general coding discussion causes the skill to inject its own rules into sessions that did not explicitly request it.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 196)May include surrounding context.

bash
# 1. 创建 skill 目录
mkdir -p ~/.openclaw/skills/cc-rules

# 2. 复制 SKILL.md
cp SKILL.md ~/.openclaw/skills/cc-rules/

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 196)May include surrounding context.

bash
# 1. 创建 skill 目录
mkdir -p ~/.openclaw/skills/cc-rules

# 2. 复制 SKILL.md
cp SKILL.md ~/.openclaw/skills/cc-rules/

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 223)May include surrounding context.

md
## 自定义

你可以编辑 `~/.openclaw/skills/cc-rules/SKILL.md` 来调整规则:

### 调整 Plan Mode 触发条件

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The title and description are written as a Chinese-only workflow specification, and the file does not indicate that language choice is optional or user-selected. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy concern unless the regional constraint is explicit and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation conditions are broad enough to auto-trigger on a very large portion of ordinary coding requests, which can cause this skill to dominate behavior outside narrowly intended contexts. In a skill system, overbroad activation is dangerous because it can silently alter how the agent handles tasks, approvals, and tool usage without clear user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
66% confidence
Finding

The language switcher emphasizes '中文 | English', which may indicate a preferred default language without explaining user choice or locale behavior. Because the file does not clarify whether language selection is user-driven, this can be interpreted as a mild locale-policy concern.

Content

No source excerpt is available for this finding.