T09 · Insecure Skill Coding Practices
- Location
scripts/url_health.py:5- Finding
Server-Side Request Forgery Through Unrestricted URL Fetching
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a simple URL checker, but it can make unrestricted network requests from the agent's environment to any supplied URL.
Install only if you are comfortable letting the agent make outbound URL checks from its runtime environment. Avoid using it on localhost, private-network, cloud metadata, credential-bearing, or untrusted redirecting URLs unless the runtime has network egress controls.
scripts/url_health.py:5Server-Side Request Forgery Through Unrestricted URL Fetching
The code generally matches the stated purpose of checking URL health and detecting HTTP/server errors using the Python standard library with no API key. However, the description specifically claims redirect chain detection, while the implementation only reports the final URL after urllib follows redirects automatically. The returned "redirects" field is always an empty list and no redirect history is captured, so that part of the declared behavior is materially overstated.
The skill advertises and necessarily performs outbound network access but does not declare any explicit tool scope or permissions boundary. This creates a transparency and governance gap: users and hosting systems may not realize the skill can initiate HTTP requests to arbitrary URLs, which increases the risk of misuse such as probing internal services or contacting sensitive endpoints.
The documentation omits a clear warning that the skill makes outbound requests to user-supplied URLs. That omission can lead users to supply untrusted or internal URLs without understanding the privacy and network implications, increasing SSRF-style risk in agent environments where the runtime has broader network reach than the user expects.
The main skill content is in English, but the closing promotional text switches to Chinese and does not provide an opt-in, translation, or explanation that the skill is region-specific. This can violate language/locale policy expectations when a skill implicitly forces or assumes a language without user choice.