mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-07-15 12:58:04 +00:00
c80462e462
* Harden skill importer against SSRF: block private targets + revalidate redirects per hop The skill importer validated only the initial URL with the lenient SSRF guard (block_private=False) and then fetched with follow_redirects=True, so a 3xx to an internal/metadata address (169.254.169.254, 127.0.0.1, RFC-1918) was still connected to — inconsistent with the hardened services/search/content.py :_get_public_url path. Add a _get_checked() helper that follows redirects manually and re-runs the SSRF guard with block_private=True on every hop, and route all three fetch sites (skills.sh unwrap, _fetch_bytes, _list_github_dir) through it. GitHub's own redirects and the final-host _assert_github_url checks are preserved. Adds hermetic regression tests (IP-literal hosts, faked HTTP layer) and updates the existing mock signature for the new block_private kwarg. Defense-in-depth: the endpoint is admin-gated (require_admin) and admins are trusted per THREAT_MODEL.md, so this is not a cross-boundary vulnerability. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test: enforce follow_redirects=False invariant in mock client Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
179 lines
4.8 KiB
Python
179 lines
4.8 KiB
Python
"""Skill URL importer — GitHub path parsing."""
|
|
import pytest
|
|
|
|
from services.memory.skill_importer import (
|
|
ResolvedSource,
|
|
SkillImportError,
|
|
_assert_github_url,
|
|
_fetch_bytes,
|
|
_list_github_dir,
|
|
parse_skill_source,
|
|
)
|
|
|
|
|
|
def test_parse_github_blob_skill_md():
|
|
src = parse_skill_source(
|
|
"https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md"
|
|
)
|
|
assert src.owner == "anthropics"
|
|
assert src.repo == "skills"
|
|
assert src.ref == "main"
|
|
assert src.path.endswith("skills/pdf/SKILL.md")
|
|
|
|
|
|
def test_parse_github_tree_directory():
|
|
src = parse_skill_source(
|
|
"https://github.com/example/my-skills/tree/develop/caveman-skill"
|
|
)
|
|
assert src.owner == "example"
|
|
assert src.repo == "my-skills"
|
|
assert src.ref == "develop"
|
|
assert src.path == "caveman-skill"
|
|
|
|
|
|
def test_parse_raw_github():
|
|
src = parse_skill_source(
|
|
"https://raw.githubusercontent.com/o/r/main/path/SKILL.md"
|
|
)
|
|
assert src.owner == "o"
|
|
assert src.repo == "r"
|
|
assert src.ref == "main"
|
|
assert src.path == "path/SKILL.md"
|
|
|
|
|
|
def test_rejects_non_github():
|
|
with pytest.raises(SkillImportError):
|
|
parse_skill_source("https://example.com/skill.md")
|
|
|
|
|
|
def test_fetch_bytes_rejects_cross_host_redirect(monkeypatch):
|
|
class _Resp:
|
|
url = "https://evil.example/secret"
|
|
status_code = 200
|
|
content = b"x"
|
|
|
|
def raise_for_status(self):
|
|
return None
|
|
|
|
class _Client:
|
|
def __init__(self, *args, **kwargs):
|
|
pass
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *args):
|
|
return False
|
|
|
|
def get(self, url, headers=None):
|
|
return _Resp()
|
|
|
|
monkeypatch.setattr("services.memory.skill_importer.httpx.Client", _Client)
|
|
monkeypatch.setattr(
|
|
"services.memory.skill_importer.check_outbound_url",
|
|
lambda url, **kwargs: (True, ""),
|
|
)
|
|
with pytest.raises(SkillImportError, match="redirect target"):
|
|
_fetch_bytes("https://raw.githubusercontent.com/o/r/main/SKILL.md")
|
|
|
|
|
|
def test_assert_github_url_allows_api_host():
|
|
_assert_github_url(
|
|
"https://api.github.com/repos/o/r/contents?ref=main",
|
|
context="redirect target",
|
|
)
|
|
|
|
|
|
def test_list_github_dir_accepts_api_github_response(monkeypatch):
|
|
monkeypatch.setattr(
|
|
"services.memory.skill_importer._fetch_text",
|
|
lambda url: "# skill\n",
|
|
)
|
|
monkeypatch.setattr(
|
|
"services.memory.skill_importer.check_outbound_url",
|
|
lambda url, **kwargs: (True, ""),
|
|
)
|
|
|
|
class _Resp:
|
|
url = "https://api.github.com/repos/o/r/contents?ref=main"
|
|
status_code = 200
|
|
|
|
def raise_for_status(self):
|
|
return None
|
|
|
|
def json(self):
|
|
return [{
|
|
"name": "SKILL.md",
|
|
"type": "file",
|
|
"download_url": "https://raw.githubusercontent.com/o/r/main/SKILL.md",
|
|
}]
|
|
|
|
class _Client:
|
|
def __init__(self, *args, **kwargs):
|
|
pass
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *args):
|
|
return False
|
|
|
|
def get(self, url, headers=None):
|
|
return _Resp()
|
|
|
|
monkeypatch.setattr("services.memory.skill_importer.httpx.Client", _Client)
|
|
|
|
out = {}
|
|
src = ResolvedSource(owner="o", repo="r", ref="main", path="")
|
|
_list_github_dir(src, "", out)
|
|
assert "SKILL.md" in out
|
|
|
|
|
|
def _mock_httpx_client(monkeypatch, response):
|
|
class _Client:
|
|
def __init__(self, *args, **kwargs):
|
|
pass
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *args):
|
|
return False
|
|
|
|
def get(self, url, headers=None):
|
|
return response
|
|
|
|
monkeypatch.setattr("services.memory.skill_importer.httpx.Client", _Client)
|
|
monkeypatch.setattr(
|
|
"services.memory.skill_importer.check_outbound_url",
|
|
lambda url, **kwargs: (True, ""),
|
|
)
|
|
|
|
|
|
def test_list_github_dir_surfaces_rate_limit(monkeypatch):
|
|
class _Resp:
|
|
url = "https://api.github.com/repos/o/r/contents?ref=main"
|
|
status_code = 403
|
|
|
|
def json(self):
|
|
return {"message": "API rate limit exceeded for 203.0.113.1"}
|
|
|
|
_mock_httpx_client(monkeypatch, _Resp())
|
|
src = ResolvedSource(owner="o", repo="r", ref="main", path="")
|
|
with pytest.raises(SkillImportError, match="rate limit"):
|
|
_list_github_dir(src, "", {})
|
|
|
|
|
|
def test_fetch_bytes_surfaces_github_error_detail(monkeypatch):
|
|
class _Resp:
|
|
url = "https://raw.githubusercontent.com/o/r/main/SKILL.md"
|
|
status_code = 403
|
|
content = b""
|
|
|
|
def json(self):
|
|
return {"message": "Forbidden"}
|
|
|
|
_mock_httpx_client(monkeypatch, _Resp())
|
|
with pytest.raises(SkillImportError, match="GitHub request failed \\(403\\): Forbidden"):
|
|
_fetch_bytes("https://raw.githubusercontent.com/o/r/main/SKILL.md")
|