Security audit

Skill Risk Splitter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local, user-directed report generator for reviewing and splitting over-broad OpenClaw skills, with no evidence of hidden execution, network access, persistence, or destructive behavior.

Install this if you are comfortable with a Chinese-language skill that can run a local Python report generator on files you choose. Avoid pointing it at sensitive directories unless you intend those files to be summarized or audited, and review any output path before writing reports.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (12)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 92% confidence
Finding: The declared purpose is narrow and governance-oriented, but the analyzed behavior indicates broader auditing and scanning capabilities, including directory scanning, pattern-based risk detection, data sampling, and report generation. This mismatch is dangerous because it can mislead users and reviewers about the true operational scope, causing them to invoke a more powerful analysis skill than intended and potentially expose sensitive local content during scans.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill advertises executable and file-manipulating behavior by referencing python3 execution and local resource/input-output handling, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization and review gap: operators and automated policy systems cannot clearly constrain or assess what the skill is allowed to access, increasing the chance of unintended shell execution or file modification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file presents all headings and instructional text exclusively in Chinese, which imposes a specific language on users. The policy for natural-language violations flags language constraints unless the skill offers a language choice or clearly documents a justified locale-specific scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The markdown template is entirely written in Chinese and labels itself as an output template, which implies the skill's generated content is expected in a specific language. There is no indication that users may choose another language or that the Chinese-only format is a documented, justified locale restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This code generates multiple user-facing report sections and guidance strings entirely in Chinese, such as headings and next-step instructions, with no option for the user to select language or locale. That creates a natural-language policy issue because the skill effectively forces a specific language without opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The directory and CSV report builders produce headings, labels, and review instructions in Chinese by default. Because these are user-visible outputs and there is no language selection mechanism, the script imposes a locale choice across more than one skill mode.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The built-in patterns detect secrets, private URLs, and dangerous shell usage across arbitrary files. That capability resembles a security scanner, which is not an obvious requirement for a skill whose stated purpose is restructuring over-broad skills into safer variants.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: These functions continue the same pattern of emitting Chinese-only headings, findings summaries, and remediation prompts. In the absence of any locale selection or explicit regional justification, this is a natural-language policy violation under the language/locale rule.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest describes a narrowly scoped refactoring aid for splitting over-broad skills into safer variants or sub-skills. However, the dispatcher supports multiple broader audit/report modes such as directory audits, CSV audits, and arbitrary pattern scanning, which are analysis capabilities not inherently tied to skill-splitting or refactoring.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The smoke test content is entirely written in Chinese, including the title and all instructions, with no indication that the skill offers a language choice or that Chinese is a required locale for a region-specific use case. This creates a natural-language policy concern because it implicitly fixes the skill's operating language without documented user opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The README lists activation examples such as '帮我把职责过杂的 skill 拆开' and '设计安全版和增强版' without clarifying boundaries for when this skill should or should not be invoked. In particular, '设计安全版和增强版' is generic enough to overlap with broader design conversations, and the file does not provide exclusion conditions or a narrowly defined trigger scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This markdown file uses Chinese throughout, including the title and all audit conclusions, with no indication that users may choose another language. Per the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.