Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. 运行 `check_quality.py`，获取评分报告
Security audit
skill-quality-checker
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local quality checker for installed OpenClaw skills, and its file-reading and optional report-writing behavior matches that purpose.
Install only if you want a Chinese-oriented local quality checker for OpenClaw skills. Review the scan path before running it, and use --output only for report locations you intend to create or overwrite.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 3. 如需详细评分标准，参考 `references/scoring-criteria.md`
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
The skill instructs the agent to run a local Python script that scans installed skills and can write reports to arbitrary output paths, but the manifest declares no tool scope such as permissions or allowed-tools. This creates a capability/metadata mismatch: the skill can drive file reads and writes without explicit declaration, which weakens reviewability and increases the chance of unintended filesystem access if the skill is invoked automatically or modified later.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger list contains broad phrases like 'evaluate skill' and 'audit skill' that can plausibly match ordinary user requests, causing the skill to activate in contexts broader than intended. Over-broad activation is dangerous here because the skill can initiate filesystem-scanning behavior over installed skills, potentially exposing metadata or generating outputs when the user did not intend to invoke this specific capability.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
L110-L111 将“包含中文触发词”和“包含英文触发词”都作为评分项，等于对技能描述施加双语要求。该要求未说明用户可选择语言，也未说明这是特定双语场景所必需，属于自然语言层面的语言/locale 策略约束。
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This Python skill is described entirely as a Chinese-only quality tool, and later its scoring logic explicitly rewards Chinese keywords while penalizing descriptions lacking them. That creates a language policy issue because the tool imposes a specific language expectation rather than offering users a language choice or documenting a justified locale restriction.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The code adds points only when the description contains Chinese characters and records missing Chinese trigger words otherwise. Because there is no user opt-in or region-specific justification, this enforces a language preference that can unfairly downgrade valid non-Chinese skills.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 71% confidence
- Finding
The natural-language description and instructions are presented in Chinese, but the trigger list includes both Chinese and English phrases. This can impose a language assumption on users without explicitly offering a language choice or documenting the locale expectation.
- Content