Back to skill

Security audit

TOSR Test Skill For Delete

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ephemeral integration-test skill that describes publishing, updating, and deleting its own test skill, with no bundled code or hidden behavior.

Install only if you understand this is an ephemeral ClawHub API lifecycle test artifact. Its documented workflow includes creating, updating, and deleting the named test skill on the real service; avoid adapting it to non-test skills unless deletion is explicitly confirmed and scoped.

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
  • 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 (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
92% confidence
Finding

The documented use of DELETE /api/v1/skills/{slug} is a high-risk operation because the slug parameter directly determines which resource is destroyed. In the context of a real API, insufficient validation or overly broad control of this parameter could enable deletion of unintended skills, making the destructive capability materially dangerous even if the described purpose is test cleanup.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly documents deletion of a skill via the live API, but it does not present a clear warning, confirmation requirement, or scope limitation around the destructive action. In a real agent setting, documenting deletion as a normal lifecycle step without user-facing caution increases the risk of unintended destructive operations against the targeted slug.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

The statement that the skill will be 'automatically deleted after the test completes' indicates autonomous execution of a destructive action without an explicit human approval checkpoint. Even though the stated target is an ephemeral test skill, automatic deletion against a real service can become dangerous if identifiers, environment boundaries, or execution context are wrong.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
## 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description is written only in Chinese while the rest of the skill content is in English, which can impose a language choice on users without opt-in or documented justification. This is a natural-language policy concern because the file does not indicate that the skill is intended only for a Chinese-language audience.

Content

No source excerpt is available for this finding.