ClawHub
Back to skill

Security audit

TOSR Publish Then Update Test

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ephemeral integration-test skill for ClawHub skill publish/update/delete lifecycle testing, with no executable payload in the artifact.

Install or run this only in a dedicated test context with credentials limited to disposable ClawHub skill resources. Confirm the target slug before any delete step, because the intended workflow uses real remote state-changing API operations.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly describes real publish, update, and delete operations against a live remote API, but it does not warn the user that executing it can create, modify, or remove remote resources. That omission increases the risk of unintended destructive actions, especially because the described workflow includes deletion and appears framed as a routine integration test.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Notes

This skill is ephemeral and will be automatically deleted after the test completes.
If you see this skill listed on clawhub, it means a test run failed to clean up properly.
Confidence
86% confidence
Finding
The note states that the skill will be automatically deleted after the test completes, indicating autonomous execution of a destructive remote action without showing any approval checkpoint. Even in a test context, automated deletion against a real API can remove resources unexpectedly or normalize running state-changing actions without operator confirmation.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
1. **Publish** — Creates a new skill via POST /api/v1/skills with multipart form data
2. **Inspect** — Retrieves skill metadata via GET /api/v1/skills/{slug}
3. **Update** — Publishes a new version of an existing skill
4. **Delete** — Removes the skill via DELETE /api/v1/skills/{slug}

## Notes
Confidence
94% confidence
Finding
The skill documents direct use of a DELETE endpoint targeting a slug parameter, which is a destructive capability and can be dangerous if the target is influenced incorrectly or used outside a tightly scoped test account. In context, this is more concerning because the skill is meant to interact with the real API lifecycle, so misuse could delete actual skills rather than disposable test artifacts.

Static analysis

No suspicious patterns detected.