Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - required folder layout check (`SKILL.md` at skill root)
Security audit
Graph Memory Zero
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed playbook for tuning OpenClaw graph-memory recall settings, with scoped config changes, verification, and rollback guidance.
Before installing, confirm you want this skill to let an agent patch graph-memory recall settings and restart OpenClaw as part of verification. Also check whether the documented SiliconFlow model and embedding endpoint is approved for your workspace data and deployment region.
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
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file specifies a Chinese trigger phrase (“达到你这套效果”) as the activation condition, which imposes a specific language for invocation. The skill also later prescribes Chinese output headings, indicating a locale/language requirement rather than offering a user choice.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The output contract requires replies to use Chinese-labeled sections such as “当前状态” and “回滚信息.” This is a natural-language policy concern because it forces a specific language for responses without documenting user opt-in or a justified locale constraint.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md ## Model stack - LLM: - `baseURL = https://api.siliconflow.cn/v1` - `model = deepseek-ai/DeepSeek-V3.2` - Embedding: - `baseURL = https://api.siliconflow.cn/v1`
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md ## Model stack - LLM: - `baseURL = https://api.siliconflow.cn/v1` - `model = deepseek-ai/DeepSeek-V3.2` - Embedding: - `baseURL = https://api.siliconflow.cn/v1`
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
The markdown specifies fixed base URLs pointing to
api.siliconflow.cnfor both LLM and embedding services. This hard-codes a region/vendor-specific endpoint in natural-language configuration guidance without any stated user choice, opt-in, or justification, which can conflict with language/locale policy expectations for user-selectable regional behavior.- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The instruction "Use this file when users ask for “more ways to download/install”" provides only a loose natural-language trigger without defining scope, exclusions, or example non-matches. This could overlap with general installation questions and cause the reference to be invoked in situations beyond its intended purpose.
- Content