The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
- capability exposure inferred + 10
- recent drift inferred + 20
- tool safety inferred + 22
- trust mitigators mixed − 17
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 10h ago · see ecosystem CVEs →
- C · 36 → C · 35
- C · 44 → C · 36
- D · 64 → C · 44
- D · 62 → D · 64
- C · 54 → D · 62
- C · 37 → C · 54
- C · 44 → C · 37
- B · 19 → C · 44
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key · dynamic exec: __import__ sink, __import__()
- 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
- medium exfiltration combo list
single tool reads + sends: fs, net
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across connected servers: this server can exfiltrate (network) while a connected dependency supplies private-data access / untrusted-content ingestion
analyzed commit 9685767 · analyzer v33 · 9h ago
skills & prompt files 13
- agent-rules phasespace-labs-palinode-9685767/examples/CLAUDE.md
- skill phasespace-labs-palinode-9685767/skill/palinode-claude-code/SKILL.md
- skill phasespace-labs-palinode-9685767/skill/palinode-memory/SKILL.md
- skill phasespace-labs-palinode-9685767/skill/palinode-session/SKILL.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/compaction.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/consolidation.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/context-assembly.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/digest.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/extraction.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/ingestion.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/nightly-consolidation.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/trajectory-extraction.md
- prompt-file phasespace-labs-palinode-9685767/specs/prompts/update.md
danger signals4
- dynamic code execution __import__ sink phasespace-labs-palinode-9685767/palinode/core/defaults.py :82
__import__("os").environ.get("PALINODE_SESSION_END_TIMEOUT", "90") - dynamic code execution __import__() phasespace-labs-palinode-9685767/tests/test_bench_perf.py :86
__import__( - suspicious endpoint 169.254.169.254 (cloud metadata) phasespace-labs-palinode-9685767/tests/integration/test_security.py :216
resp = client.post("/ingest-url", json={"url": "http://169.254.169.254/latest/meta-data/"}) - committed secret Anthropic key phasespace-labs-palinode-9685767/tests/test_security_log_redaction.py :34
sk-ant…(37 chars, redacted)
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:phasespace-labs/palinode/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 phasespace-labs.