pp-domain-goat

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the domain-goat-pp-cli binary through the Bash tool, passing user-supplied arguments directly to the shell environment.
  • [DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> feature that enables the agent to POST command output and analysis results to arbitrary external URLs. Additionally, the tool can be configured to send local feedback to a remote endpoint via the DOMAIN_GOAT_FEEDBACK_ENDPOINT environment variable.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process domain registration data from external RDAP, WHOIS, and DNS services which are outside the agent's control.
  • Ingestion points: Data from external domain registries is ingested via the check, rdap, whois, and sync commands in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate untrusted external data from system instructions.
  • Capability inventory: The skill has the capability to execute shell commands and perform network operations via the domain-goat-pp-cli binary.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved RDAP/WHOIS records before they are processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill's setup instructions involve downloading the CLI binary from the vendor's official NPM package and GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:06 AM