farai 0.1.9 → 0.2.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "farai",
-  "version": "0.1.9",
+  "version": "0.2.1",
   "private": false,
   "type": "module",
   "description": "Cyber-first freestyle local AI agent",

package/src/agent-skills/library/payload-protocol-crafting/SKILL.md

@@ -9,7 +9,7 @@ When a target service speaks something other than plain HTTP (a legacy or custom
 e.g. LPD, a proprietary binary protocol, etc.), trial-and-error against the full exploit is slow
 and confusing. Work bottom-up instead:
 
-1. **read the spec first.** look up the RFC or protocol documentation (`web_search`, `web_fetch`, or `http_request`)
+1. **read the spec first.** look up the RFC or protocol documentation (`internet_search`, `internet_fetch`, or `http_request`)
    before writing any code — legacy protocols usually have a short, precise spec (e.g. RFC 1179
    for LPD) that tells you the exact byte sequence/framing expected, far faster than guessing.
 2. **build the smallest possible reproducer.** write a minimal script that performs just the

package/src/agent-skills/library/searchsploit/SKILL.md

@@ -13,6 +13,6 @@ description: How to search for and validate public exploits with the exploit_sea
 - Prefer the smallest, most targeted PoC over a fully-weaponized Metasploit module when you just
   need to confirm a vulnerability exists — easier to reason about and adapt if it doesn't work
   out of the box.
-- If no local exploit-db entry matches, fall back to `web_search`/`web_fetch` for the CVE/product
+- If no local exploit-db entry matches, fall back to `internet_search`/`internet_fetch` for the CVE/product
   name — public writeups often show the exact working payload for CTF-style intentionally
   vulnerable services (which are frequently older/unpatched versions on purpose).