ClawHub
Back to skill

Security audit

TOSR Test Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed lifecycle-test skill for ClawHub publishing operations, with no executable payload or hidden behavior found.

Install or run this only if you intend to participate in ClawHub lifecycle testing. It is not a general-purpose user skill, and any real API operations should use test-scoped credentials and the named test resource.

SkillSpector

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

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly states it performs create, update, and delete operations against the real API, but it does not present a prominent user warning or require confirmation for those destructive actions. This is dangerous because a user or downstream agent could invoke the skill in a production context without appreciating that it will mutate and delete real resources.

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
84% confidence
Finding
The note that the skill will be 'automatically deleted after the test completes' indicates autonomous execution of a destructive operation without an explicit approval checkpoint. Even if intended for cleanup, autonomous deletion against a real service can remove resources unexpectedly or under the wrong account/context if safeguards are weak.

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
90% confidence
Finding
The documented DELETE operation targets a parameterized real API endpoint and, in the stated lifecycle, is part of an automated workflow. This is dangerous because if the slug or execution context is manipulated, the skill could delete unintended resources on the live service, especially when combined with insufficient validation or confirmation.

Static analysis

No suspicious patterns detected.