Short-term memory proxy gateway with proactive memory surfacing for AI agents
- vulnerabilities attested + 25
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 12
- trust mitigators mixed − 3
attested 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.
graded 3m ago · see ecosystem CVEs →
- C · 57 → E · 81
- B · 32 → C · 57
- C · 44 → B · 32
- C · 49 → C · 44
- A · 0 → C · 49
- high dangerous code
committed secret: Anthropic key, GitLab token
analyzed commit 1e839cd · analyzer v28 · 2h ago
skills & prompt files 1
- agent-rules memtomem-memtomem-stm-1e839cd/CLAUDE.md
danger signals2
- committed secret Anthropic key memtomem-memtomem-stm-1e839cd/tests/test_privacy.py :281
sk-ant…(47 chars, redacted) - committed secret GitLab token memtomem-memtomem-stm-1e839cd/tests/test_privacy.py :284
glpat-…(38 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:memtomem/memtomem-stm/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 memtomem.