Local, private browser for AI coding CLI sessions (Claude Code + Copilot + Codex) — unified search, usage/cost dashboard, resume-from-anywhere, cross-CLI bridge, reasoning trails, MCP server
- capability exposure inferred + 20
- recent drift inferred + 12
- 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.
graded 8m ago · see ecosystem CVEs →
- B · 17 → C · 41
- B · 20 → B · 17
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key, GitHub fine-grained PAT
analyzed commit 580f3cc · analyzer v28 · 4h ago
skills & prompt files 4
danger signals2
- committed secret Anthropic key mpankaj151-session-browser-580f3cc/tests/test_smoke.py :177
sk-ant…(37 chars, redacted) - committed secret GitHub fine-grained PAT mpankaj151-session-browser-580f3cc/tests/test_smoke.py :186
github…(38 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:mpankaj151/session-browser/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 mpankaj151.