Loading the registry…
Local-first coding agent memory for Claude Code and OpenAI Codex
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
112 critical findings reported by cisco-skill-scanner, agent-audit-kit, 45 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/majiayu000/remem, 707 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- remem-ai
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
467 findings · 35.6s
v0.3.26
190 findings · 24.2s
v0.1.0
2 findings · 30.1s
v0.1.0
13 findings · 30.1s
v0.1.0
0 findings · 22.1s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.2s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 31, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 672 findings across every scanner that examined this package. 67 of 112 findings rated critical by their scanner were among the dismissals.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
283 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_coercive_injection_generic, opt.nerlo-rules.nerlo-install-pipe-to-shell, PIPELINE_TAINT_FLOW and 11 more · Files: /repo/specs/GH717/SKILL.md, /repo/docs/competitive-analysis.md, /repo/docs/research/seo-agent-skill-plugin-audit-2026-06-19.md and 113 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
95 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_credential_harvesting_generic, DATA_EXFIL_JS_FS_ACCESS and 2 more · Files: /repo/plugins/remem/scripts/remem-runtime.test.js, /repo/src/session_rollup/tests/poisoning.rs, /repo/plugins/remem/apps/remem/server.test.js and 1 more · reported by cisco-skill-scanner, agent-audit-kit
60 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, CLAUDE.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
7 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001, MANIFEST_INVALID_NAME · Files: .github/workflows/ci.yml, .github/workflows/release.yml, /repo/.github/ISSUE_TEMPLATE/SKILL.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
59 AAK-HEALTHCARE-AI-004
Files: eval/golden.json, .remem/dream-cluster-failure-isolation.md, eval/claims/claims-registry.schema.json and 56 more · reported by agent-audit-kit
25 AAK-TAINT-002
Files: src/observe/hook.rs, src/adapter/common/tests.rs, src/eval/coding_bench/runner.rs and 1 more · reported by agent-audit-kit
22 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/npm/remem/scripts/install.js, /repo/plugins/remem/apps/remem/server.js, /repo/plugins/remem/scripts/remem-runtime.js · reported by cisco-skill-scanner
18 ASSET_PROMPT_INJECTION
Files: /repo/eval/public/memory/artifacts/adversarial-policy-v2/remem_default-benign-quoted-instruction-001/reader_input.txt, /repo/eval/public/memory/artifacts/adversarial-policy-v2/remem_default-benign-quoted-instruction-001/retrieved_evidence.json, /repo/eval/public/memory/suites/adversarial-policy/suite.json and 1 more · reported by cisco-skill-scanner
17 DATA_EXFIL_JS_NETWORK
Files: /repo/plugins/remem/apps/remem/public/widget.js, /repo/plugins/remem/apps/remem/server.js, /repo/npm/remem/scripts/install.js and 1 more
Critical risks: shell execution, credential access, and data exfiltration
The artifact contains critical findings related to potential shell execution in `plugins/remem/apps/remem/server.js` and `src/eval/coding_bench/runner.rs`. It also exposes credentials in `src/memory/retrieval_enrichment/tests.rs` and `src/adapter/common/tests.rs`. Additionally, there are high-severity findings indicating network egress of sensitive data and file system access for data exfiltration.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
15 MANIFEST_MISSING_LICENSE
Files: /repo/.agents/skills/remem-first-run-smoke/SKILL.md, /repo/.agents/skills/remem-plugin-version-sync/SKILL.md, /repo/plugins/remem/skills/remem/SKILL.md and 12 more · reported by cisco-skill-scanner
14 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/npm/remem/bin/remem.js, /repo/npm/remem/scripts/install.js, /repo/plugins/remem/scripts/remem-runtime.js · reported by cisco-skill-scanner
12 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/eval/SKILL.md, /repo/.remem/SKILL.md and 9 more · reported by cisco-skill-scanner
11 AAK-SECRET-004
Files: src/context/injection_gate.rs, src/adapter/common/tests.rs, src/cli/actions/codex_memory_import/tests.rs and 4 more · reported by agent-audit-kit
7 HIDDEN_DATA_FILE
Files: /repo/plugins/remem/.codex-plugin/plugin.json, /repo/.agents/plugins/marketplace.json, /repo/.agents/skills/remem-plugin-version-sync/SKILL.md and 3 more · reported by cisco-skill-scanner
3 AAK-METIS-SCORING-SINK-001
Files: eval/locomo/run_locomo.py, eval/local/run_local_eval.py · reported by agent-audit-kit
3 EXCESSIVE_FILE_COUNT
Files: /repo/eval/public/., /repo/., /repo/eval/. · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/plugins/remem, /repo/plugins/remem/apps/remem, /repo/npm/remem · reported by cisco-skill-scanner
2 AAK-SECRET-003
Files: src/user_context/non_retention.rs, src/user_context/candidates/tests.rs · reported by agent-audit-kit
2 AAK-SECRET-008
Files: src/memory/retrieval_enrichment/tests.rs · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/plugins/remem/apps/remem/server.js · reported by nerlo-behavioral
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/eval/repo/eval/README.md, /repo/eval/locomo/repo/eval/locomo/README.md · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .agents/plugins/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: plugins/remem/apps/remem/server.js · reported by agent-audit-kit
1 AAK-MCP-018
Files: plugins/remem/apps/remem/server.js · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: plugins/remem/apps/remem/server.js · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 COMPOUND_EXTRACT_EXECUTE
Files: /repo/install.sh · reported by cisco-skill-scanner
1 COMPOUND_FETCH_EXECUTE
Files: /repo/scripts/smoke_native_web_api.sh · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/.remem/SKILL.md · reported by cisco-skill-scanner
1 YARA_prompt_injection_unicode_steganography
Files: /repo/site/assets/remem-demo.gif · reported by cisco-skill-scanner
1 YARA_tool_chaining_abuse_generic
Files: /repo/src/user_context/non_retention.rs · reported by cisco-skill-scanner
Showing 25 of 100; the rest are in the per-scanner reports above.