analyzing-malicious-url-with-urlscan
URLScan.io is a free service for scanning and analyzing suspicious URLs. It captures screenshots, DOM content, HTTP transactions, JavaScript behavior, and network connections of web pages in an isolat
52
58%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/analyzing-malicious-url-with-urlscan/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt shows and instructs use of the URLScan API with a header "API-Key: your-api-key" and automation scripts, which requires inserting the user's API key verbatim into requests or generated code, creating a direct secret-exposure risk.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow submits a user-supplied URL to URLScan and then ingests URLScan API JSON fields (including rendered DOM content/requests) into the agent’s context; because the scanned page content is outsider-authored, this is an indirect prompt-injection exposure path via URLScan’s returned prose/DOM-derived text.
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
e612f49
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.