Ae1
High
- Category
- analysis-evasion
- Content
- [ ] `SKILL.md` — frontmatter has name, version, description
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
ClawHub Skill Publisher
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward ClawHub publishing assistant, but users should be aware it can edit skill files and guide a publish workflow.
Install only if you want an agent to help revise ClawHub skill files and prepare publishing. Review generated patches before accepting them, keep research installs in a temporary directory, and approve the final clawhub publish command only when the slug, version, changelog, and account are correct.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)
Ae1
High
- Category
- analysis-evasion
- Content
- [ ] `SKILL.md` — frontmatter has name, version, description
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
- [ ] `SKILL.md` — frontmatter has name, version, description
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
- [ ] `SKILL.md` — frontmatter has name, version, description
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
- [ ] `SKILL.md` — frontmatter has name, version, description
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Missing User Warnings
Medium
- Confidence
- 95% confidence
- Finding
- The README states that the skill will patch README/SKILL files and walk the user through publishing, but it does not clearly warn up front that local files will be modified and that the workflow proceeds toward a publish action. This can lead users to invoke the skill without understanding that it may alter their repository contents and advance a release workflow, increasing the chance of unintended changes or accidental publication.
Static analysis
No suspicious patterns detected.