ClawHub
Back to skill

Security audit

DNS Doctor

Security checks for vulnerabilities and agentic risk

Overview

The skill provides disclosed DNS and email checks, with optional account reads and human control over DNS changes.

Scans create public reports, so avoid domains you need kept private. Use a non-sensitive email for testing: the provider receives it and shares a redacted excerpt with an AI provider. Supply an API token only if you want account reads, review proposed DNS records before publishing, and authorize any paid calls.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The description focuses on diagnostics for any domain, but this chunk also accesses authenticated account-monitoring resources that are not disclosed. The watched look-alike query aligns with the declared look-alike functionality, and token authentication alone is not a mismatch. The mismatch is the additional account-alert and monitoring-readiness access, not the absence of other advertised diagnostics from this partial code chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The request targets an account-scoped 'mine' resource, a capability not disclosed in the description. Although it uses the declared API provider, its apparent purpose is account-domain retrieval rather than any of the listed diagnostic operations. The exact response contents cannot be confirmed from the code alone.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 5)May include surrounding context.

md
name: dns-doctor
description: DNS diagnostics and email authentication for any domain, via the DNS Doctor public API. Scan SPF, DKIM, DMARC, MX, DNS health, blacklists and domain/TLS expiry; look up registration; see which close look-alike names resolve or accept mail; check a record on the domain's own nameservers and its propagation from six vantage points; count SPF lookups and audit SPF includes; validate or generate DMARC records; test how one real email authenticates (SPF, DKIM, DMARC) by sending it to a single-use address; check BIMI logo setup. Fix records come from a validating engine, never guessed and are presented for a human to publish. Free per caller; x402 pay-per-call past the cap.
license: Apache-2.0
compatibility: Requires curl and outbound HTTPS to dnsdoctor.dev.
metadata:
  {
    "homepage": "https://dnsdoctor.dev/methodology",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 290)May include surrounding context.

bash
# Did the change land? (kind: spf|dmarc|txt|mx|cname|a|aaaa)
curl -s -X POST https://dnsdoctor.dev/api/tools/check-record \
  -H 'Content-Type: application/json' \
  -d '{"domain": "example.com", "kind": "dmarc", "expected_value": "v=DMARC1; p=none"}'