The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides examples of using standard shell utilities (curl, jq, sed, sort) and established open-source security tools (subfinder, amass, dnsx) to perform subdomain discovery. These commands are integral to the skill's primary function as an OSINT tool.
[EXTERNAL_DOWNLOADS]: The skill fetches data from reputable and well-known services such as crt.sh (a widely used Certificate Transparency search engine) and references other industry-standard sources like Google's CT log list and urlscan.io. These network operations are intended for data retrieval from trusted platforms.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external, untrusted sources such as CT logs and passive DNS results.
Ingestion points: Data enters the agent's context through curl requests and external tools like subfinder in SKILL.md.
Boundary markers: No specific delimiters are mentioned to separate processed domain data from the agent's instructions.
Capability inventory: The skill uses subprocess calls to execute several CLI tools (curl, jq, subfinder, amass, dnsx) as part of its core workflow.
Sanitization: Structured data parsing is performed using jq to extract specific fields from JSON responses.

find-hidden-subdomains