Loading the registry…
Memory you can verify — a trust layer between an AI coding agent and its own past: per-hit staleness verdicts, claim-level use attribution, measured effectiveness, episodic run-state. MCP-native, local-first, MIT, no cloud.
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.
30 critical findings reported by cisco-skill-scanner, agent-audit-kit, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 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/0Mattias/bettermemory, 226 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- bettermemory
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
107 findings · 45.9s
v0.3.26
67 findings · 76.2s
v0.1.0
1 finding · 38.4s
v0.1.0
0 findings · 38.4s
v0.1.0
0 findings · 42.4s
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 |
| Aug 1, 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 175 findings across every scanner that examined this package. 26 of 30 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 1 finding stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
85 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: AAK-SECRET-003, AAK-SECRET-001, SECRET_GITHUB_TOKEN and 14 more · Files: tests/test_server_confirm_regate.py, tests/test_proposals.py, tests/test_consolidate_llm.py and 21 more · reported by agent-audit-kit, cisco-skill-scanner
29 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-IPI-WILD-CORPUS-001, AAK-HEALTHCARE-AI-004, FILE_MAGIC_MISMATCH and 3 more · Files: tests/test_index.py, docs/api.md, docs/swarm-convergence-plan.md and 17 more · reported by agent-audit-kit, cisco-skill-scanner
5 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/SKILL.md · 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.
9 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/bench/longmemeval/cm_run.py, /repo/bench/rot/screen.py, /repo/src/bettermemory/llm.py · reported by cisco-skill-scanner
8 MANIFEST_MISSING_LICENSE
Files: /repo/plugin/skills/bettermemory/SKILL.md, /repo/SKILL.md, /repo/plugin/SKILL.md and 5 more · reported by cisco-skill-scanner
7 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugin/SKILL.md, /repo/bench/dedup/SKILL.md and 4 more · reported by cisco-skill-scanner
6 AAK-IPI-WILD-CORPUS-001
Files: CHANGELOG.md, bench/rot/frame/top-pypi-packages-2026-07-01.json, src/bettermemory/models.py and 2 more · reported by agent-audit-kit
4 HIDDEN_DATA_FILE
Files: /repo/bench/rot/.screen-cache.json, /repo/.pre-commit-config.yaml, /repo/.githooks/commit-msg · reported by cisco-skill-scanner
3
The model could have called any of these a false positive and did not.
2 AAK-ANTHROPIC-SDK-001
Files: examples/programmatic_client.py, tests/eval/live_adapters.py · reported by agent-audit-kit
2 AAK-MCP-STDIO-CMD-INJ-001
Files: examples/programmatic_client.py, tests/eval/live_adapters.py · reported by agent-audit-kit
2 SQL_INJECTION_STRING_FORMAT
Files: /repo/src/bettermemory/index.py · reported by cisco-skill-scanner
1 The model did not answer for these findings.
Rules: DATA_EXFIL_SENSITIVE_FILES · Files: /repo/tests/test_platform_fixture_lint.py · reported by cisco-skill-scanner
Critical findings include command injection and SQL injection.
The artifact contains critical findings for potential command injection in `examples/programmatic_client.py` and `tests/eval/live_adapters.py`, and SQL injection in `/repo/src/bettermemory/index.py`. High severity findings indicate potential for resource abuse in `/repo/bench/toolcost/run.py` and `/repo/src/bettermemory/scope_match.py`, and credential access leading to network egress in `/repo/src/bettermemory/llm.py`. Additionally, there are multiple instances of high severity findings related to wild corpus data in various files, and medium severity findings for undeclared network activity.
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.
Files: /repo/bench/toolcost/run.py, /repo/src/bettermemory/scope_match.py · reported by cisco-skill-scanner
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/bench/rot/repo/bench/rot/PREREGISTRATION.md, /repo/bench/longmemeval/repo/bench/longmemeval/CLAUDE-MEM-ADAPTER.md · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: bench/rot/README.md, bench/longmemeval/README.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-005
Files: plugin/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-007
Files: plugin/.mcp.json · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/src/bettermemory/doctor.py · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/bettermemory/llm.py · reported by nerlo-behavioral