Back to skill

Security audit

TOSR Publish Then Update Test

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a disclosed ephemeral ClawHub lifecycle test skill, though its metadata description is a placeholder and users should recognize it may create, update, and delete a test skill through the real API.

Install or run this only if you intend to exercise ClawHub publish, update, and delete behavior against the real API. Use test credentials and verify the slug is the intended ephemeral test skill before allowing deletion.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
92% confidence
Finding

The skill documents a DELETE operation against /api/v1/skills/{slug}, a destructive API action whose safety depends entirely on how the slug parameter is chosen and authorized. In a skill that interacts with the real API and performs lifecycle management, insufficient validation or confirmation could allow unintended deletion of arbitrary skills or abuse of high-privilege tool access.

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

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description at L04 is a placeholder Chinese sentence meaning roughly 'one-sentence description of the Skill’s function and usage scenario,' while the body documentation at L12-L14 states the skill is an automated integration test for the clawhub REST API lifecycle. This creates a clear description-behavior mismatch because the declared description does not describe the actual intended operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description field is written in Chinese with no indication that language selection is optional or configurable. This is a natural-language locale policy concern because the skill metadata presents a fixed language choice rather than offering the user a language or locale preference.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
84% confidence
Finding

The skill explicitly describes autonomous deletion of a resource after test completion, which indicates self-directed state-changing behavior against a real external API. Even if intended for cleanup, autonomous destructive actions can remove resources without an explicit user confirmation step and become dangerous if the target identifier or execution context is 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.