mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-14 14:12:44 +00:00
c2828f2b9b
unbroker finds where a consenting person's info is exposed across data brokers and people-search sites and files the removals, running as far as each site allows and handing only genuinely human-only steps (hard CAPTCHA, gov-ID, phone, fax) back as an end-of-run digest. - Deterministic stdlib CLI (scripts/pdd.py) owns config, dossiers+consent, the broker DB, tier planning, the ledger, email, and the autonomous action queue; the agent scans/submits with native tools (web_extract, browser_*, delegate_task, cronjob, terminal). - Verify-before-disclose, least-disclosure (never volunteers SSN), consent gate, opaque ids, optional age-at-rest encryption, file-locked ledger. - Jurisdiction-aware (CCPA/CPRA, GDPR, generic); CA DROP one-shot covers the state registry (~545) in a single request; BADBOOL + curated people-search coverage; scheduled re-scan for re-listing. - No CAPTCHA-solving services or anti-bot bypass; browser email mode needs no stored password. - 85 hermetic tests (tests/skills/test_unbroker_skill.py; SMTP/IMAP via injected fakes, registry via CSV fixtures). Ships placeholder data only. Broker dataset adapted from BADBOOL (Yael Grauer, CC BY-NC-SA 4.0).
79 lines
2.1 KiB
Python
79 lines
2.1 KiB
Python
"""Filesystem paths for the unbroker skill (stdlib only).
|
|
|
|
All per-subject data lives under PDD_DATA_DIR (default: $HERMES_HOME/unbroker),
|
|
which is the same trust boundary Hermes uses for .env and OAuth tokens.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
|
|
def hermes_home() -> Path:
|
|
return Path(os.environ.get("HERMES_HOME") or (Path.home() / ".hermes"))
|
|
|
|
|
|
def data_dir() -> Path:
|
|
override = os.environ.get("PDD_DATA_DIR")
|
|
return Path(override) if override else hermes_home() / "unbroker"
|
|
|
|
|
|
def config_path() -> Path:
|
|
return data_dir() / "config.json"
|
|
|
|
|
|
def subjects_dir() -> Path:
|
|
return data_dir() / "subjects"
|
|
|
|
|
|
def subject_dir(subject_id: str) -> Path:
|
|
return subjects_dir() / subject_id
|
|
|
|
|
|
def dossier_path(subject_id: str) -> Path:
|
|
return subject_dir(subject_id) / "dossier.json"
|
|
|
|
|
|
def ledger_path(subject_id: str) -> Path:
|
|
return subject_dir(subject_id) / "ledger.json"
|
|
|
|
|
|
def audit_path(subject_id: str) -> Path:
|
|
return subject_dir(subject_id) / "audit.jsonl"
|
|
|
|
|
|
def evidence_dir(subject_id: str) -> Path:
|
|
return subject_dir(subject_id) / "evidence"
|
|
|
|
|
|
def skill_root() -> Path:
|
|
"""The skill directory (parent of scripts/)."""
|
|
return Path(__file__).resolve().parent.parent
|
|
|
|
|
|
def brokers_dir() -> Path:
|
|
return skill_root() / "references" / "brokers"
|
|
|
|
|
|
def brokers_cache_path() -> Path:
|
|
"""Live broker snapshot pulled from BADBOOL (merged under the curated DB)."""
|
|
return data_dir() / "brokers-cache" / "badbool.json"
|
|
|
|
|
|
def registry_cache_path() -> Path:
|
|
"""CA Data Broker Registry snapshot (separate coverage lane; DROP/email, not scanned)."""
|
|
return data_dir() / "brokers-cache" / "ca-registry.json"
|
|
|
|
|
|
def age_identity_path() -> Path:
|
|
"""age identity (private key) used for at-rest encryption when enabled.
|
|
|
|
Defaults beside the data; point PDD_AGE_IDENTITY at a separate volume/token
|
|
for real key separation from the encrypted data.
|
|
"""
|
|
override = os.environ.get("PDD_AGE_IDENTITY")
|
|
return Path(override) if override else data_dir() / "age-identity.txt"
|
|
|
|
|
|
def templates_dir() -> Path:
|
|
return skill_root() / "templates"
|