Local-first AI memory for coding agents. NouGenShards stores reusable "shards" in a local SQLite + FTS5 database with outcome-weighted retrieval, so agents recall what worked instead of re-prompting. Your agents have prompts — mine have shards.
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 3
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 · 56 → D · 64
- C · 44 → C · 56
- B · 32 → C · 44
- A · 0 → B · 32
No known CVEs for this server.
- high dangerous code
committed secret: HuggingFace token, Anthropic key · dynamic exec: __import__ sink, eval()/exec()
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
- medium dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed commit 996ca6e · analyzer v33 · 1d ago
skills & prompt files 4
danger signals11
- dynamic code execution __import__ sink Who-Visions-NouGenShards-996ca6e/src/nougen_shards/models_client.py :922
__import__("os").getenv("NOUGEN_NUM_PREDICT", "1400"))}} - dynamic code execution eval()/exec() Who-Visions-NouGenShards-996ca6e/tests/test_app_coverage.py :27
exec(compile(ast.fix_missing_locations(mod), "app.py", "exec"), ns) - dynamic code execution eval()/exec() Who-Visions-NouGenShards-996ca6e/tests/test_app_readthrough.py :22
exec(compile(ast.fix_missing_locations(mod), APP, "exec"), ns) - dynamic code execution eval()/exec() Who-Visions-NouGenShards-996ca6e/tests/test_original_timestamp.py :42
exec(compile(ast.fix_missing_locations(mod), "app.py", "exec"), ns) - dynamic code execution __import__ sink Who-Visions-NouGenShards-996ca6e/tests/test_recall_warmup.py :17
ns = {"os": __import__("os"), "core": core, "time": __import__("time"), "logging": __import__("logging")} - dynamic code execution eval()/exec() Who-Visions-NouGenShards-996ca6e/tests/test_recall_warmup.py :18
exec(compile(ast.fix_missing_locations(ast.Module(body=fns, type_ignores=[])), "app.py", "exec"), ns) - suspicious endpoint 169.254.169.254 (cloud metadata) Who-Visions-NouGenShards-996ca6e/tests/test_audit_fixes.py :139
("https://169.254.169.254/latest/meta-data/", False), # cloud metadata SSRF - suspicious endpoint 1.2.3.4 Who-Visions-NouGenShards-996ca6e/tests/test_audit_fixes.py :238
assert cloud._pinned_ip_for("https://1.2.3.4") is None # IP literal: no pin - committed secret HuggingFace token Who-Visions-NouGenShards-996ca6e/tests/test_auth_check.py :35
hf_thi…(38 chars, redacted) - committed secret Anthropic key Who-Visions-NouGenShards-996ca6e/tests/test_brain_scan.py :32
sk-ant…(49 chars, redacted) - committed secret Anthropic key Who-Visions-NouGenShards-996ca6e/ts/src/test/brain_scan.test.ts :52
sk-ant…(49 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:Who-Visions/NouGenShards/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 Who-Visions.