Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` is present
Security audit
Publish To ClawHub
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed publishing workflow for local OpenClaw skills, with expected file edits, GitHub sync, and ClawHub publishing steps.
Install this only if you want an agent to help edit and publish skills. Before using it, confirm the target repository, review all generated changes and any English rewriting, complete authentication through browser, SSH, or a credential manager, and verify no private material will be published.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Rogue AgentSelf-Modification, Session Persistence
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` is present
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` is present
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` is present
Self-Modification
High
- Category
- Rogue Agent
- Confidence
- 85% confidence
- Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
- Content
copy updated skill files plus temporary README into the clone
git add -A git status git commit -m "Update skill and README" git push origin main
text
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 80% confidence
- Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Content
md Rules: - never ask the user to paste a long-lived token into chat unless there is no safer option - prefer browser login, credential manager, or SSH when available - never store credentials in files - never force-push without explicit user confirmation
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill directs converting descriptions and instructions to English for broader release without requiring explicit user confirmation. That can cause unintended modification of user-authored content, meaning, tone, or licensing-sensitive text before publication, especially when the original language choice is intentional. In a publishing workflow, silent content transformation is more dangerous because it can propagate altered material to public registries and GitHub.
- Content
Static analysis
No suspicious patterns detected.