T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:92- Finding
Overbroad Access to OpenClaw Persistent Memory
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed collaboration guide, but it grants broad cross-agent memory access and persistent task dispatch without enough scoping or user control.
Install only in a trusted local Hermes/OpenClaw setup. Limit use to explicit user-approved collaboration tasks, keep messages inside memory/collab where possible, avoid reading unrelated OpenClaw memory, and do not expose --json diagnostic output or delegate publishing unless you have reviewed the exact skill path and release details.
SKILL.md:92Overbroad Access to OpenClaw Persistent Memory
SKILL.md:36Persistent Cross-Agent Instruction Channel Without Trust Validation
SKILL.md:193Exposure of Complete System Prompt and Agent Capability Inventory
The file’s natural-language content, examples, and operating instructions are entirely in Chinese, and it gives prescriptive workflow guidance without indicating that another language is supported or that the user may choose their preferred locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
This is a duplicate of the persistent shared-memory behavior at line 39 and remains a real issue for the same reason: it encourages durable file-based inter-agent communication without trust boundaries. In a collaborative agent environment, such persistence can amplify prompt injection and stale-instruction risks.
python3.11 ~/.hermes/scripts/openclaw-bridge.py read memory/projects/
python3.11 ~/.hermes/scripts/openclaw-bridge.py write memory/collab/hermes-to-openclaw.md "内容"
**使用场景**:
This is a duplicate of the persistent shared-memory behavior at line 39 and remains a real issue for the same reason: it encourages durable file-based inter-agent communication without trust boundaries. In a collaborative agent environment, such persistence can amplify prompt injection and stale-instruction risks.
python3.11 ~/.hermes/scripts/openclaw-bridge.py read memory/projects/
python3.11 ~/.hermes/scripts/openclaw-bridge.py write memory/collab/hermes-to-openclaw.md "内容"
**使用场景**:
This duplicate finding is still valid because the skill again normalizes direct persistent writes as the mechanism for collaboration. The context makes it more dangerous than ordinary note-taking because the receiving agent is expected to observe and potentially act on the stored content.
1. **openclaw agent CLI 超时** — GLM5 在 NVIDIA 上不稳定,用 bridge 直接调 API 绕过
2. **openclaw.json 修复记录** — includeDefaultMemor->includeDefaultMemory,移除非法 memory.flush 键
3. **skills symlink escape 警告** — 不影响使用
4. **消息发送混淆** — `chat` 命令只是调用模型对话,不会发送消息给OpenClaw。要发送消息必须使用 `write memory/collab/` 或直接写入文件
## 常见错误
This duplicate finding is still valid because the skill again normalizes direct persistent writes as the mechanism for collaboration. The context makes it more dangerous than ordinary note-taking because the receiving agent is expected to observe and potentially act on the stored content.
1. **openclaw agent CLI 超时** — GLM5 在 NVIDIA 上不稳定,用 bridge 直接调 API 绕过
2. **openclaw.json 修复记录** — includeDefaultMemor->includeDefaultMemory,移除非法 memory.flush 键
3. **skills symlink escape 警告** — 不影响使用
4. **消息发送混淆** — `chat` 命令只是调用模型对话,不会发送消息给OpenClaw。要发送消息必须使用 `write memory/collab/` 或直接写入文件
## 常见错误
Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.
# 1. 检查skill目录结构
ls -la /Users/a1234/.openclaw/workspace/skills/ops-maintenance/
# 2. 检查SKILL.md格式
cat /Users/a1234/.openclaw/workspace/skills/ops-maintenance/SKILL.md
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.
ls -la /Users/a1234/.openclaw/workspace/skills/ops-maintenance/
# 2. 检查SKILL.md格式
cat /Users/a1234/.openclaw/workspace/skills/ops-maintenance/SKILL.md
# 3. 发布到clawhub.ai
clawhub publish /Users/a1234/.openclaw/workspace/skills/ops-maintenance \