Back to skill

Security audit

Opportunity Deep Dive

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent business-research workflow, but it can automatically publish sensitive business reports to a fixed Feishu knowledge base without a clear final user approval step.

Install only if you intend reports to be published into the specified Feishu knowledge base and are comfortable sharing the business idea, strategy, market research, and generated plan with whoever can access that space. Before use, require the agent to show the destination, document tree, and full content for review, and approve the Feishu write explicitly.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:82
Finding

Reports Are Automatically Published to a Hard-Coded External Knowledge Base

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad conversational expressions such as '帮我分析这个方向' and 'XX值得做吗', which can cause the skill to activate during ordinary discussion rather than explicit user intent to run a multi-step workflow. In this skill, accidental activation is more dangerous because it can initiate extensive downstream actions, including composing reports and potentially writing them to Feishu.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description states that the final report will be uploaded to a Feishu knowledge base, but it does not require explicit user consent at the point of data export. This creates a real risk of unauthorized disclosure of user-provided business ideas, internal strategy, or sensitive research to an external collaborative system.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

2.1 商机评分(opportunity-scout)

text
读取技能:/root/.openclaw/workspace/skills/opportunity-scout/SKILL.md
执行:对该方向进行评分,输出需求/竞争/可行性/变现四个维度得分

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

2.2 市场研究(market-research)

text
读取技能:/root/.openclaw/workspace/skills/market-research/SKILL.md
执行:市场规模估算、客户验证、数据来源

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

2.3 竞品分析(competitive-analysis)

text
读取技能:/root/.openclaw/workspace/skills/competitive-analysis/SKILL.md
执行:识别竞品、分析优劣势、找差距和切入点

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

2.4 风险评估(opportunity-assessment)

text
读取技能:/root/.openclaw/workspace/skills/opportunity-assessment/SKILL.md
执行:风险分级、待确认事项、是否建议投入

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

2.5 商业模式设计(business-model-canvas)

text
读取技能:/root/.openclaw/workspace/skills/business-model-canvas/SKILL.md
执行:设计商业模式画布,验证商业逻辑

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

2.6 商业计划书(business-plan)

text
读取技能:/root/.openclaw/workspace/skills/business-plan/SKILL.md
执行:撰写完整商业计划书(12个部分)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written as Chinese report templates and does not indicate that language selection is optional. Under the policy rules, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
95% confidence
Finding

Referencing '/root/.openclaw/workspace/skills/business-plan/SKILL.md' exposes the existence, naming, and location of another internal skill, enabling skill enumeration. In an agent environment, that context can help an attacker infer available capabilities, craft targeted prompts, or probe for unintended cross-skill access, making this more dangerous than a generic documentation leak.

Content

Scanner excerpt · references/templates.md (reported line 240)May include surrounding context.

md
11. 风险评估
12. 退出策略

详见:/root/.openclaw/workspace/skills/business-plan/SKILL.md

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

整个技能的触发、流程和输出要求均以中文固定表达,未说明可根据用户偏好切换语言。按照语言/地区策略,若技能默认强制单一语言而不给用户选择,属于自然语言层面的策略问题。

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The template discloses an absolute internal filesystem path to another skill, which leaks implementation details and creates unnecessary coupling to resources outside this skill's declared scope. Even without direct code execution, such path disclosure can aid environment mapping, future prompt/path probing, or unauthorized cross-skill reference attempts.

Content

No source excerpt is available for this finding.