Web Application Reconnaissance — Hub

Sub-skills under this directory:

Overall recon workflow, scope rules, and handoff format are loaded into your system prompt at agent boot — no load_skill call needed for them.

Tag-Driven Fast Paths

When the orchestrator passes challenge tags, skip straight to the matching sub-skill:

HTTP Request Deduplication Pattern

When iterating parameters (IDs, pages, paths), always deduplicate via recon/probed.txt to avoid re-probing the same URLs after context summarization:

URL="http://<TARGET>/api/resource/$ID"
if grep -Fxq "$URL" recon/probed.txt 2>/dev/null; then
  echo "SKIP: $URL"
else
  echo "$URL" >> recon/probed.txt
  curl -sS "$URL" -o /tmp/probe.html -w '%{http_code}\n'
  head -10 /tmp/probe.html
fi

Resume rule: Before any scan loop, check tail -1 recon/probed.txt to find the last probed item and continue from there — not from the beginning.

Stop rule: If 5 consecutive probes return the same status code + same response size (±50 bytes), stop that enumeration axis and pivot to a different surface.

Output files

./
├── ffuf_<target>_dirs.json         # Directory fuzzing results
├── ffuf_<target>_vhosts.json       # Virtual host discovery
├── ffuf_<target>_api.json          # API endpoint fuzzing
├── web_sensitive_<target>.txt      # Sensitive file check results
├── js_endpoints_<target>.txt       # Extracted JS endpoints
├── wpscan_<target>.json            # WordPress scan (if applicable)
└── web_recon_<target>_summary.md   # Consolidated web findings