# delete_file

Delete a file or directory on the HexStrike server.

Agent View of the PolicyLayer registry record for `delete_file`. HTML page: https://policylayer.com/tools/hexstrike-ai/delete-file

## Facts

- Tool: `delete_file`
- Server: Hexstrike Ai (`0x4m4/hexstrike-ai`) — https://policylayer.com/tools/hexstrike-ai.md
- Homepage: https://github.com/0x4m4/hexstrike-ai
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "delete_file",
    "arguments": {}
  }
}
```

## Why delete_file is rated Critical

Deletion of files or directories cannot be undone and represents permanent loss of data. On a pentesting/offensive security server, this poses critical risk if an AI agent misuses the tool, as it could delete critical system files, evidence, configurations, or other essential data.

From the tool's own definition: "Tool name is 'delete_file' with description stating it can 'Delete a file or directory on the HexStrike server.' This explicitly performs irreversible deletion of data."

## Use case

AI agents call delete_file to permanently remove resources in Hexstrike Ai, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Hexstrike Ai:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_file"
  ]
}
```

## Other tools on Hexstrike Ai (149)

- `clear_cache` — Destructive — https://policylayer.com/tools/hexstrike-ai/clear-cache.md
- `advanced_payload_generation` — Execute — https://policylayer.com/tools/hexstrike-ai/advanced-payload-generation.md
- `ai_generate_attack_suite` — Execute — https://policylayer.com/tools/hexstrike-ai/ai-generate-attack-suite.md
- `ai_generate_payload` — Execute — https://policylayer.com/tools/hexstrike-ai/ai-generate-payload.md
- `ai_reconnaissance_workflow` — Execute — https://policylayer.com/tools/hexstrike-ai/ai-reconnaissance-workflow.md
- `ai_test_payload` — Execute — https://policylayer.com/tools/hexstrike-ai/ai-test-payload.md
- `ai_vulnerability_assessment` — Execute — https://policylayer.com/tools/hexstrike-ai/ai-vulnerability-assessment.md
- `amass_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/amass-scan.md
- `angr_symbolic_execution` — Execute — https://policylayer.com/tools/hexstrike-ai/angr-symbolic-execution.md
- `api_fuzzer` — Execute — https://policylayer.com/tools/hexstrike-ai/api-fuzzer.md
- `arjun_parameter_discovery` — Execute — https://policylayer.com/tools/hexstrike-ai/arjun-parameter-discovery.md
- `arjun_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/arjun-scan.md
- `arp_scan_discovery` — Execute — https://policylayer.com/tools/hexstrike-ai/arp-scan-discovery.md
- `autorecon_comprehensive` — Execute — https://policylayer.com/tools/hexstrike-ai/autorecon-comprehensive.md
- `autorecon_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/autorecon-scan.md
- `binwalk_analyze` — Execute — https://policylayer.com/tools/hexstrike-ai/binwalk-analyze.md
- `browser_agent_inspect` — Execute — https://policylayer.com/tools/hexstrike-ai/browser-agent-inspect.md
- `bugbounty_authentication_bypass_testing` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-authentication-bypass-testing.md
- `bugbounty_business_logic_testing` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-business-logic-testing.md
- `bugbounty_comprehensive_assessment` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-comprehensive-assessment.md
- `bugbounty_file_upload_testing` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-file-upload-testing.md
- `bugbounty_osint_gathering` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-osint-gathering.md
- `bugbounty_reconnaissance_workflow` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-reconnaissance-workflow.md
- `bugbounty_vulnerability_hunting` — Execute — https://policylayer.com/tools/hexstrike-ai/bugbounty-vulnerability-hunting.md
- `burpsuite_alternative_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/burpsuite-alternative-scan.md
- `burpsuite_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/burpsuite-scan.md
- `checkov_iac_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/checkov-iac-scan.md
- `clair_vulnerability_scan` — Execute — https://policylayer.com/tools/hexstrike-ai/clair-vulnerability-scan.md
- `comprehensive_api_audit` — Execute — https://policylayer.com/tools/hexstrike-ai/comprehensive-api-audit.md
- `create_attack_chain_ai` — Execute — https://policylayer.com/tools/hexstrike-ai/create-attack-chain-ai.md
- …and 119 more: https://policylayer.com/tools/hexstrike-ai.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=hexstrike-ai · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/hexstrike-ai