The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous shell command templates for DNS reconnaissance (dig, nslookup, host) and cloud service manipulation (aws s3, az webapp, heroku domains:add, flyctl, surge). These commands are intended to be executed by the agent to fulfill the skill's primary purpose of subdomain takeover detection and verification.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data, such as DNS records and HTTP response bodies, to match fingerprints for various service providers. This introduces a surface for indirect prompt injection if the processed external data contains malicious instructions intended to influence the agent's behavior.
Ingestion points: DNS record values and HTTP response content (headers and bodies) as described in SKILL.md.
Boundary markers: Absent; no delimiters or instructions are provided to the agent to ignore potentially embedded instructions in the external data.
Capability inventory: The skill utilizes network requests (curl), DNS queries (dig), and various cloud provider CLI tools (aws, az, heroku, flyctl) across both SKILL.md and references/takeover-techniques.md.
Sanitization: No sanitization or validation steps are described for the external content before processing.

subdomain-takeover