Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 9
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- C · 50 → C · 58
- C · 56 → C · 50
- C · 48 → C · 56
- A · 0 → C · 48
No known CVEs for this server.
- high dangerous code
dynamic exec: pickle.loads(), __import__()
analyzed commit 920d1c9 · analyzer v33 · 18h ago
skills & prompt files 12
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/architectural-decisions/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/change-review/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/code-health/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/codebase-exploration/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/dead-code-cleanup/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/claude-code/skills/pre-modification/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/architectural-decisions/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/change-review/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/code-health/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/codebase-exploration/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/dead-code-cleanup/SKILL.md
- skill repowise-dev-repowise-920d1c9/plugins/codex/skills/pre-modification-check/SKILL.md
danger signals8
- dynamic code execution pickle.loads() repowise-dev-repowise-920d1c9/packages/core/src/repowise/core/analysis/health/walk_cache.py :75
value = pickle.loads(blob) - dynamic code execution pickle.loads() repowise-dev-repowise-920d1c9/packages/core/src/repowise/core/ingestion/parse_cache.py :172
parsed: Any = pickle.loads(blob) - dynamic code execution __import__() repowise-dev-repowise-920d1c9/packages/core/src/repowise/core/ingestion/parser.py :820
mod = __import__(spec.grammar_package) - dynamic code execution __import__() repowise-dev-repowise-920d1c9/tests/unit/cli/test_health_rescore_gate.py :175
lines = inspect.getsource(__import__(module_name, fromlist=["*"])).splitlines() - dynamic code execution pickle.loads() repowise-dev-repowise-920d1c9/tests/unit/generation/test_models.py :227
assert pickle.loads(pickle.dumps(config)) == config - dynamic code execution pickle.loads() repowise-dev-repowise-920d1c9/tests/unit/ingestion/test_centrality_cache.py :214
restored = pickle.loads(pickle.dumps(cache)) - dynamic code execution pickle.loads() repowise-dev-repowise-920d1c9/tests/unit/ingestion/test_parse_cache.py :137
payload = pickle.loads(unseal(cache_file.read_bytes(), domain=_CACHE_DOMAIN)) - dynamic code execution __import__() repowise-dev-repowise-920d1c9/tests/unit/persistence/test_page_tree_wiring.py :51
module = __import__(module_name, fromlist=["*"])
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:repowise-dev/repowise/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of repowise-dev.