skills/alpoxdev/hypercore/crawler/Gen Agent Trust Hub

crawler

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and templates recommend the installation and use of specialized third-party libraries for bot evasion, such as 'patchright', 'rebrowser-patches', 'camoufox', and 'curl_cffi'. These are non-standard dependencies from independent maintainers on public registries.
  • [COMMAND_EXECUTION]: The workflow relies on the 'playwriter' tool to execute arbitrary JavaScript code within a browser session. This capability is used to explore website functionality, identify interactive elements, and extract structured data.
  • [PROMPT_INJECTION]: As the skill is designed to crawl and analyze content from untrusted external websites, it is vulnerable to indirect prompt injection. Malicious instructions embedded in a target website's content (such as in HTML comments or metadata) could potentially influence the agent's analysis or the code it generates during its automated workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 08:02 PM
Security Audit — agent-trust-hub — crawler