T05 · Unauthorized Access and Privilege Escalation
- Location
handler.py:6- Finding
Unrestricted URL Fetching Enables Server-Side Request Forgery
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
handler.py:6Unrestricted URL Fetching Enables Server-Side Request Forgery
SKILL.md:35Hard-Coded API Credential Exposed in Skill Documentation
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.
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.
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.
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.