The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the Nuclei scanner from the official ProjectDiscovery GitHub repository using the Go toolchain (go install -v github.com/projectdiscovery/nuclei/v3/cmd/nuclei@latest).
[COMMAND_EXECUTION]: The skill facilitates the execution of the nuclei command-line tool for security scanning, template updates, and report generation across various formats (JSON, Markdown, SARIF).
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process data from external, untrusted web targets during vulnerability scans.
Ingestion points: Untrusted data enters the agent context through target URLs passed to the -u flag and bulk target lists passed to the -l flag in SKILL.md.
Boundary markers: There are no explicit markers or instructions provided to the agent to treat scan results as untrusted content.
Capability inventory: The skill provides full access to the nuclei scanner's capabilities, including network requests and file writing for reports.
Sanitization: The skill instructions do not specify any sanitization or validation of the scanner's output before it is returned to the agent context.

nuclei-scan