Security audit

login-digitalme

Security checks for vulnerabilities and agentic risk

Overview

This SMS login skill matches its stated purpose, but it handles phone numbers, SMS codes, cookies, and tokens with weak endpoint disclosure and a command that can expose full session credentials.

Install only if you trust and control the configured SMS_LOGIN_BASE_URL endpoint. Before use, require HTTPS on an approved host, avoid printing raw login responses or cookie jars, redact tokens from all output, and make users explicitly confirm that their phone number and SMS code will be sent to that service.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:54
Finding: Authentication Tokens Exposed Through Standard Output
Content: View full analysis
` or the stolen co ...[truncated 613 chars]
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:11
Finding: Sensitive SMS Authentication Data May Be Sent to an Untrusted or Plaintext Endpoint
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

External Transmission

Medium

Category: Data Exfiltration
Confidence: 88% confidence
Finding: The skill metadata hard-codes an external host/IP and declares it as the primary environment for authentication operations, which means sensitive phone-login data may be transmitted to a remote endpoint without any trust, ownership, or transport-security assurances in the documentation. Using a raw IP and port for an auth service raises additional concern because it bypasses recognizable domain validation and gives no indication of TLS, certificate validation expectations, or data-handling guarantees.
Content: Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.
md
openclaw: requires: bins: - curl - jq env: - 180.184.28.174:30080

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation guidance is broad enough to trigger on common account-related requests such as phone login or registration, which can cause the agent to invoke a sensitive authentication workflow without sufficiently narrow scoping or confirmation. Because this skill handles phone numbers, one-time codes, tokens, and session cookies, overbroad triggering increases the chance of unnecessary collection or transmission of sensitive data.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill directs the agent to transmit highly sensitive authentication data, including phone numbers, verification codes, tokens, and cookies, but does not require an explicit user-facing privacy and security warning before doing so. This is dangerous because users may not understand that their credentials and session artifacts are being sent to an external service, increasing privacy, account-takeover, and consent risks.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 95% confidence
Finding: The login step sends a phone number and one-time verification code to an external endpoint and captures cookies, directly handling authentication secrets and session material. In this context, external transmission is especially dangerous because compromise, misdirection, logging, or interception of these values could enable account access or session hijacking.
Content: Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.
向用户索要短信中的验证码后，发起登录：

bash
curl -s -c - -X POST "${SMS_LOGIN_BASE_URL}/api/v1/auth/phone/login" \ -H "Content-Type: application/json" \ -d '{"phone": "'"${PHONE}"'", "code": "'"${CODE}"'"}' | jq .