T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:82- Finding
Reports Are Automatically Published to a Hard-Coded External Knowledge Base
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:82Reports Are Automatically Published to a Hard-Coded External Knowledge Base
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.
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.
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.
2.1 商机评分(opportunity-scout)
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 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.
2.2 市场研究(market-research)
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 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.
2.3 竞品分析(competitive-analysis)
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 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.
2.4 风险评估(opportunity-assessment)
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 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.
2.5 商业模式设计(business-model-canvas)
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 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.
2.6 商业计划书(business-plan)
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)
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.
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.
11. 风险评估
12. 退出策略
详见:/root/.openclaw/workspace/skills/business-plan/SKILL.md
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。
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.