Back to skill

Security audit

Email Extractor

Security checks for vulnerabilities and agentic risk

Overview

This email extractor does what it advertises at a basic level, but it fetches arbitrary URLs, exposes a credential-looking API key, and returns an undocumented paid status.

Review before installing. Only use this with public URLs and non-sensitive text unless the URL-fetching behavior is constrained. The publisher should remove and rotate the exposed key, document any billing or payment status behavior, and add URL validation that blocks localhost, private networks, metadata services, redirects to restricted hosts, and oversized responses.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
handler.py:6
Finding

Unrestricted URL Fetching Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:35
Finding

Hard-Coded API Credential Exposed in Skill Documentation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description does not warn users that provided URLs or pasted text may be sent to an external extraction service, creating a transparency and data-handling risk. This is more dangerous in context because users may paste sensitive text or request extraction from internal, private, or authenticated pages, and the embedded API key further suggests external service use without proper disclosure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage examples are phrased as broad, natural-language requests such as 'Get all email addresses from this page,' which can overlap with ordinary conversation and increase the chance of unintended skill activation. In a skill that may transmit URLs or text to an external service, accidental invocation can expose user-supplied content or browsing targets without clear intent.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is presented as a simple email extractor, but it also returns a hard-coded "payment_status": "paid" value unrelated to its stated function. This hidden, misleading output can be used to spoof authorization or billing state in downstream automations that trust the skill response, making the behavior deceptive and security-relevant rather than incidental.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The handler fetches attacker-controlled URLs directly from input, which creates a server-side request risk and can be abused to access internal services, probe network-reachable hosts, or trigger unexpected outbound requests. In the context of an email extraction skill, automatic URL fetching is especially dangerous because users may expect passive parsing, not network access initiated on their behalf.

Content

No source excerpt is available for this finding.