Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 目标 skill 目录和 `SKILL.md` 是否包含在该提交中
Security audit
发布验证 · Release Proof Builder
Security checks for vulnerabilities and agentic risk
Overview
This skill is a release-verification helper whose repository, registry, and isolated install checks are disclosed and aligned with its purpose.
Before installing, expect the skill to inspect Git repository state, query ClawHub registry data, and optionally perform an isolated ClawHub install to prove availability. Verify the target slug/version carefully, and remember that the optional install check may increment public install/download metrics.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - 目标 skill 目录和 `SKILL.md` 是否包含在该提交中
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill advertises broad trigger phrases such as '帮我证明这个 skill 已经真正发布成功' and '检查 GitHub 推送、Actions 和 ClawHub 状态是不是一致', which are generic enough to overlap with ordinary conversation about releases. In agent environments that auto-route based on natural-language matching, this can cause unintended activation, leading the skill to access repository and registry state when the user did not explicitly intend to invoke it.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This markdown file contains all operational guidance in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The file presents core descriptive content in mixed Chinese and English, but does not explain whether output language follows the user's preference or whether the mixed-language behavior is intentional. This can create a language/locale policy issue if the skill implicitly forces or defaults to a language style without user opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
All user-facing instructional content in this file is written in Chinese, and the document does not offer an alternative language or indicate that the skill is intended only for a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Static analysis
No suspicious patterns detected.