Faithful Task Executor

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 11:18 AM UTC
• Version: 1.0.0

Overview

This is a disclosed Chinese-language task-management skill that creates local task rule files and may coordinate subagents, with no evidence of hidden code, exfiltration, or destructive behavior.

Install this if you want a Chinese-localized workflow for preserving task rules and coordinating subagents. Before using it on sensitive or costly tasks, confirm when it should activate, review the generated `.task-rules/rules.md`, and keep subagent concurrency within limits you are comfortable with.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The activation phrases are generic tasking language such as '执行这个任务' and '完成以下要求', which are likely to appear in ordinary user prompts. This can cause the skill to trigger unintentionally and take over workflow orchestration, rule persistence, and subagent behavior in contexts where the user did not explicitly request this skill, increasing the chance of instruction interference and unexpected agent actions.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: Most of the operational instructions and examples are presented in Chinese, which can impose a language preference on users without explicit opt-in. The file includes a small amount of English for contribution and license text, but it does not offer a language choice for the skill's main behavior or document that the skill is intentionally region-specific.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The README uses "执行这个任务" as the example invocation, which is a very generic phrase that could match ordinary user requests rather than a narrowly scoped activation condition. The document does not provide any explicit trigger constraints or negative examples to clarify when this skill should activate versus when it should not.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: This markdown file presents the skill’s description, activation conditions, workflow, and examples exclusively in Chinese, which effectively forces a language/locale for users interacting with the skill. There is no opt-in language selection, bilingual guidance, or stated region-specific justification for the restriction.

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: The template title and all instructional content are written in Chinese, which imposes a specific language on users of the skill. Under the policy, locale or language constraints should either be optional, user-selectable, or explicitly justified as region-specific.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The entire template is written in Chinese and presents all required sections, confirmations, and lock statements only in that language. There is no natural-language indication that users may choose another language or locale, which can violate a policy requiring language choice or user opt-in.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The entire template, including headings, field labels, instructions, and examples, is written only in Chinese, which imposes a specific language on skill users and subagents. The file does not indicate that Chinese is optional, user-selected, or required for a region-specific purpose, so it creates a language-policy concern.

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: The entire template, including headings, field labels, and instructions, is written only in Chinese, which imposes a specific language/locale on users. The file does not mention that Chinese is optional, configurable, or intended only for a Chinese-speaking context.

Natural-Language Policy Violations

Low

• Confidence: 89% confidence
• Finding: The package description is written entirely in Chinese, which indicates a fixed language choice in the skill's natural-language metadata. There is no accompanying note offering alternative languages or explaining that the skill is intentionally limited to a Chinese-speaking audience, which may violate language/locale policy requirements.

Unverifiable Dependency: openclaw has 16 known advisory(ies) (CVE-2026-53846 (OpenClaw: Workspace .env npm_execpath could influence bundled runtime dependency); CVE-2026-32064 (OpenClaw's andbox browser noVNC observer lacked VNC authentication); CVE-2026-32006 (OpenClaw has a BlueBubbles group allowlist mismatch via DM pairing-store fallbac) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low

• Category: Supply Chain
• Confidence: 40% confidence
• Finding: Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

Static analysis

No suspicious patterns detected.