File size: 9,592 Bytes
9452af2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
"""
Rhodawk AI — Vulnerability Chain Analyzer
==========================================
Documents how primitive findings (individual assumption gaps + PoC results)
might combine into higher-severity chains.

ETHICAL CONSTRAINTS:
  - Chains are THEORETICAL proposals documented for human review
  - No chain is automatically executed
  - All chain proposals are stored with status PENDING_HUMAN_REVIEW
  - Human operator must approve or reject every chain before any further action

Orchestrated by Nous Hermes 3 via OpenRouter.
"""

from __future__ import annotations

import hashlib
import json
import os
import re
import sqlite3
import time
from typing import Optional

import requests

OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY", "")
HERMES_MODEL = os.getenv(
    "RHODAWK_RESEARCH_MODEL",
    "nousresearch/hermes-3-llama-3.1-405b:free",
)
CHAIN_DB = os.getenv("RHODAWK_CHAIN_DB", "/data/chain_memory.sqlite")


def _init_db() -> None:
    os.makedirs(os.path.dirname(CHAIN_DB), exist_ok=True)
    conn = sqlite3.connect(CHAIN_DB)
    conn.executescript("""
        CREATE TABLE IF NOT EXISTS primitive_findings (
            id          TEXT PRIMARY KEY,
            repo        TEXT NOT NULL,
            gap_id      TEXT NOT NULL,
            severity    TEXT,
            description TEXT,
            triggered   INTEGER DEFAULT 0,
            confidence  TEXT DEFAULT 'UNKNOWN',
            created_at  REAL,
            harness_out TEXT
        );
        CREATE TABLE IF NOT EXISTS chains (
            id                TEXT PRIMARY KEY,
            repo              TEXT NOT NULL,
            primitive_ids     TEXT NOT NULL,
            description       TEXT,
            chained_severity  TEXT,
            confidence        TEXT,
            conditions        TEXT,
            theoretical_impact TEXT,
            human_notes       TEXT,
            status            TEXT DEFAULT 'PENDING_HUMAN_REVIEW',
            created_at        REAL,
            human_approved    INTEGER DEFAULT 0,
            human_reviewer    TEXT,
            reviewed_at       REAL
        );
    """)
    conn.commit()
    conn.close()


def store_primitive(
    repo: str,
    gap_id: str,
    severity: str,
    description: str,
    triggered: bool,
    confidence: str = "UNKNOWN",
    harness_result: Optional[dict] = None,
) -> str:
    """Persist a primitive finding from the harness execution."""
    _init_db()
    finding_id = hashlib.sha256(
        f"{repo}:{gap_id}:{time.time()}".encode()
    ).hexdigest()[:16]
    conn = sqlite3.connect(CHAIN_DB)
    conn.execute(
        """INSERT OR REPLACE INTO primitive_findings
           (id, repo, gap_id, severity, description, triggered, confidence, created_at, harness_out)
           VALUES (?,?,?,?,?,?,?,?,?)""",
        (
            finding_id, repo, gap_id, severity, description,
            1 if triggered else 0, confidence, time.time(),
            json.dumps(harness_result or {}),
        ),
    )
    conn.commit()
    conn.close()
    return finding_id


def analyze_chains(repo: str) -> list[dict]:
    """
    Ask Hermes to propose vulnerability chains from stored primitives.

    Returns THEORETICAL proposals — all tagged PENDING_HUMAN_REVIEW.
    Nothing is executed automatically.
    """
    _init_db()
    conn = sqlite3.connect(CHAIN_DB)
    rows = conn.execute(
        """SELECT id, gap_id, severity, description, triggered, confidence
           FROM primitive_findings WHERE repo = ?
           ORDER BY created_at DESC""",
        (repo,),
    ).fetchall()
    conn.close()

    if len(rows) < 2:
        return []

    primitives_text = "\n".join(
        f"- [{r[0]}] Gap: {r[1]} | Sev: {r[2]} | Triggered: {bool(r[4])} "
        f"| Confidence: {r[5]} | {r[3][:120]}"
        for r in rows
    )

    headers = {
        "Authorization": f"Bearer {OPENROUTER_API_KEY}",
        "Content-Type": "application/json",
        "HTTP-Referer": "https://rhodawk.ai",
    }
    payload = {
        "model": HERMES_MODEL,
        "messages": [
            {
                "role": "system",
                "content": (
                    "You are a senior security researcher conducting responsible vulnerability research. "
                    "Analyse primitive findings and propose THEORETICAL vulnerability chains for human review. "
                    "Be rigorous and conservative — only propose chains that are logically sound based on "
                    "the available evidence. Mark any speculation clearly. Output valid JSON only."
                ),
            },
            {
                "role": "user",
                "content": (
                    f"Analyse these primitive findings from {repo} and identify plausible chains.\n\n"
                    f"PRIMITIVES:\n{primitives_text}\n\n"
                    "Output ONLY this JSON:\n"
                    '{"chains": [{'
                    '"primitive_ids": ["id1","id2"],'
                    '"description": "Step-by-step logical chain",'
                    '"chained_severity": "P1|P2|P3",'
                    '"confidence": "HIGH|MEDIUM|LOW",'
                    '"required_conditions": ["condition1"],'
                    '"theoretical_impact": "What an attacker could theoretically achieve",'
                    '"human_verification_needed": "What a human researcher must manually verify before treating this as real"'
                    "}]}"
                ),
            },
        ],
        "max_tokens": 2048,
        "temperature": 0.1,
    }

    try:
        resp = requests.post(
            "https://openrouter.ai/api/v1/chat/completions",
            headers=headers, json=payload, timeout=120,
        )
        resp.raise_for_status()
        raw = resp.json()["choices"][0]["message"]["content"]

        match = re.search(r"\{[\s\S]*\}", raw)
        if not match:
            return []

        data = json.loads(match.group())
        chains = data.get("chains", [])

        conn = sqlite3.connect(CHAIN_DB)
        for chain in chains:
            chain_id = hashlib.sha256(
                f"{repo}:{':'.join(chain.get('primitive_ids', []))}:{time.time()}".encode()
            ).hexdigest()[:16]
            chain["id"] = chain_id
            conn.execute(
                """INSERT OR IGNORE INTO chains
                   (id, repo, primitive_ids, description, chained_severity, confidence,
                    conditions, theoretical_impact, status, created_at)
                   VALUES (?,?,?,?,?,?,?,?,'PENDING_HUMAN_REVIEW',?)""",
                (
                    chain_id, repo,
                    json.dumps(chain.get("primitive_ids", [])),
                    chain.get("description", ""),
                    chain.get("chained_severity", "P3"),
                    chain.get("confidence", "LOW"),
                    json.dumps(chain.get("required_conditions", [])),
                    chain.get("theoretical_impact", ""),
                    time.time(),
                ),
            )
        conn.commit()
        conn.close()
        return chains

    except Exception as e:
        return [{"error": str(e)}]


def get_pending_chains(repo: Optional[str] = None) -> list[dict]:
    _init_db()
    conn = sqlite3.connect(CHAIN_DB)
    if repo:
        rows = conn.execute(
            """SELECT id, repo, description, chained_severity, confidence, status, created_at
               FROM chains WHERE repo=? AND status='PENDING_HUMAN_REVIEW'
               ORDER BY created_at DESC""",
            (repo,),
        ).fetchall()
    else:
        rows = conn.execute(
            """SELECT id, repo, description, chained_severity, confidence, status, created_at
               FROM chains WHERE status='PENDING_HUMAN_REVIEW'
               ORDER BY created_at DESC""",
        ).fetchall()
    conn.close()
    return [
        {
            "id": r[0], "repo": r[1], "description": r[2],
            "severity": r[3], "confidence": r[4], "status": r[5], "created_at": r[6],
        }
        for r in rows
    ]


def get_all_primitives(repo: Optional[str] = None) -> list[dict]:
    _init_db()
    conn = sqlite3.connect(CHAIN_DB)
    if repo:
        rows = conn.execute(
            "SELECT id, repo, gap_id, severity, description, triggered, confidence, created_at "
            "FROM primitive_findings WHERE repo=? ORDER BY created_at DESC",
            (repo,),
        ).fetchall()
    else:
        rows = conn.execute(
            "SELECT id, repo, gap_id, severity, description, triggered, confidence, created_at "
            "FROM primitive_findings ORDER BY created_at DESC",
        ).fetchall()
    conn.close()
    return [
        {
            "id": r[0], "repo": r[1], "gap_id": r[2], "severity": r[3],
            "description": r[4], "triggered": bool(r[5]),
            "confidence": r[6], "created_at": r[7],
        }
        for r in rows
    ]


def approve_chain(chain_id: str, reviewer: str) -> bool:
    _init_db()
    conn = sqlite3.connect(CHAIN_DB)
    conn.execute(
        "UPDATE chains SET status='HUMAN_APPROVED', human_approved=1, "
        "human_reviewer=?, reviewed_at=? WHERE id=?",
        (reviewer, time.time(), chain_id),
    )
    conn.commit()
    conn.close()
    return True


def reject_chain(chain_id: str, reviewer: str) -> bool:
    _init_db()
    conn = sqlite3.connect(CHAIN_DB)
    conn.execute(
        "UPDATE chains SET status='HUMAN_REJECTED', human_reviewer=?, reviewed_at=? WHERE id=?",
        (reviewer, time.time(), chain_id),
    )
    conn.commit()
    conn.close()
    return True