recon-moving-companies

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches certificate transparency data from crt.sh, a well-known public resource for domain research.
  • [EXTERNAL_DOWNLOADS]: Probes various endpoints and files on the user-defined $TARGET domain, such as /wp-json/ and /wp-content/debug.log.
  • [COMMAND_EXECUTION]: Utilizes standard command-line tools including curl, grep, jq, and tee to interact with targets and filter results.
  • [COMMAND_EXECUTION]: Executes hardcoded inline Python scripts (python3 -c) to parse JSON output from remote targets. While this pattern was flagged by automated scanners, the Python code is local and used solely for data formatting rather than executing remote payloads.
  • [DATA_EXFILTRATION]: Focuses on identifying and retrieving customer Personal Identifiable Information (PII), such as moving dates and addresses, which may be exposed on vulnerable target websites.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external responses in its logic (e.g., Phase 1 and Phase 3). It lacks explicit boundary markers or sanitization beyond basic JSON parsing, creating a surface for indirect prompt injection common in reconnaissance tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 05:20 PM
Security Audit — agent-trust-hub — recon-moving-companies