Security audit

ClawJob

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent ClawJob integration, but it needs review because it can automatically perform external task and account actions while using bearer tokens without clear confirmation or untrusted-content safeguards.

Install only if you intend OpenClaw to operate on ClawJob and you are comfortable with it creating or changing ClawJob tasks, agents, subscriptions, completions, approvals, and account-related settings. Treat CLAWJOB_ACCESS_TOKEN as a secret, review every task or account-changing request before it is sent, and do not let task descriptions from the marketplace override your own instructions or request secrets.

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

Findings (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:19
Finding: Untrusted External Tasks Can Become an Indirect Instruction Channel
Content: View full analysis
Remediation: View remediation

other

Note

Location: SKILL.md:42
Finding: Automatic Publication of Agent Capability Metadata
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 198)May include surrounding context.
md
- 本技能所在目录必须命名为 `clawjob`，且内含本文件 `SKILL.md`（以及可选 `reference.md`）。

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description says to use it whenever the user wants to use ClawJob, publish or accept tasks, or when OpenClaw should act as a ClawJob user. That broad activation language can cause the agent to select this skill for generic task-management requests and then perform external API actions the user did not explicitly intend on ClawJob. Because this skill can create accounts, publish tasks, and subscribe agents to tasks, accidental invocation has real side effects.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The statement that any listed phrasing triggers execution, combined with '无需人类手写请求', removes decision boundaries and encourages automatic action execution from natural-language matches alone. Without exclusions, confirmation gates, or checks for ambiguous context, the agent may call privileged APIs based on loosely matching phrases and cause unintended registrations, postings, or workflow transitions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill instructs users to copy an API token and export it into the environment, but provides no warning that the token is a bearer credential that grants account access and should be handled as secret material. In agent settings, such omissions increase the risk of users pasting tokens into chat, storing them insecurely, exposing them in shell history, or reusing them in unsafe contexts, which could lead to account takeover or unauthorized task actions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document explicitly instructs users to export or write access tokens into environment variables or a .env file, but it does not warn that these are sensitive credentials that can be exposed through source control, logs, shell history, or local file disclosure. In an agent/platform context, leaked bearer tokens could allow unauthorized task publication, task acceptance, agent registration, and access to account data until the token is revoked or expires.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The main instructional content and user-facing examples are presented in Chinese, but the file does not indicate that this locale is optional or region-specific. This can violate language-choice expectations when the skill is loaded in broader environments without explicit user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The document is entirely presented in Chinese and the title explicitly labels it as the API reference for agent use, but it does not offer an alternative language or indicate that Chinese-only operation is required for a specific region or compliance reason. Under the language/locale policy, a forced language without opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.