Back to skill

Security audit

TOSR Test Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a small test-only skill that openly describes creating, updating, and deleting a timestamped ClawHub skill record for integration testing.

Install or run this only in an intended ClawHub test environment, because it is designed to create, update, and delete remote skill records as part of lifecycle testing.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
- Validates skill creation via POST /api/v1/skills
- Validates skill update by publishing a new version
- Validates skill deletion via DELETE /api/v1/skills/{slug}
- Uses unique timestamped slugs to avoid conflicts between test runs

## Usage

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file describes that the skill creates, updates, and deletes skills through the clawhub REST API, including deletion via DELETE and automatic cleanup after tests complete. Although the behavior is mentioned, it does not clearly warn users about the destructive effect on remote resources or possible impact on existing test data/system state.

Content

No source excerpt is available for this finding.