ClawHub
Back to skill

Security audit

Sovereign Test Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed test-generation guide with no executable payloads or hidden privileged behavior.

Before installing, expect this skill to help your agent inspect project code and draft or modify test files. Review generated tests before running them, especially integration tests that touch real databases, files, network clients, or business workflows.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

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 · EXAMPLES.md (reported line 422)May include surrounding context.

md
});

  // ============================================================
  // DELETE /tasks/:id -- Delete Task
  // ============================================================
  describe('DELETE /tasks/:id', () => {
    const authHeader = { Authorization: 'Bearer valid-token' };

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 · EXAMPLES.md (reported line 424)May include surrounding context.

md
});

  // ============================================================
  // DELETE /tasks/:id -- Delete Task
  // ============================================================
  describe('DELETE /tasks/:id', () => {
    const authHeader = { Authorization: 'Bearer valid-token' };

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · EXAMPLES.md (reported line 1031)May include surrounding context.

md
| 7 | Numbers only | `"12345"` | `"12345"` | Works, but is it a valid slug for your system? |
| 8 | Single character | `"A"` | `"a"` | Works, but verify |
| 9 | maxLength truncates mid-word | `slugify("hello world", { maxLength: 7 })` | `"hello-w"` | Truncated mid-word looks broken. Consider truncating at word boundary. |
| 10 | maxLength = 0 | `slugify("hello", { maxLength: 0 })` | `""` | `substring(0, 0)` returns empty string |
| 11 | maxLength negative | `slugify("hello", { maxLength: -1 })` | `""` | `substring(0, -1)` returns empty string in JS |
| 12 | Custom separator with regex special chars | `slugify("hello world", { separator: '.' })` | Broken: `.` is regex special char | The `\-\-+` replacement uses hardcoded `-`, won't clean `.` duplicates |
| 13 | null input | `slugify(null)` | `"null"` | `.toString()` converts null to the string "null" |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 802)May include surrounding context.

md
async fn fetches_user_from_remote_api() {
            let mut mock_client = MockHttpClient::new();
            mock_client.expect_get()
                .with(eq("https://api.example.com/users/1"))
                .returning(|_| Ok(r#"{"id":1,"name":"Remote User"}"#.to_string()));

            let service = RemoteUserService::new(mock_client);

Static analysis

No suspicious patterns detected.