Loading the registry…
Persistent, encrypted memory engine for AI agents — MCP JSON-RPC stdio server
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.
54 critical findings reported by cisco-skill-scanner, agent-audit-kit, 51 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- perseus-vault
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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
253 findings · 202.7s
v0.3.26
44 findings · 109.3s
v0.1.0
8 findings · 109.8s
v0.1.0
31 findings · 109.9s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.5s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 20.5s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
3 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 ·n/a: not applicable | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Jul 29, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | 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 336 findings across every scanner that examined this package. 2 of 54 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.
54 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_FETCH_EXECUTE, PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell and 5 more · Files: /repo/examples/SKILL.md, /repo/docs/integration/claude-code.md, /repo/docs/integration/cursor.md and 15 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
19 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 · Files: .github/workflows/clawhub-publish.yml, .github/workflows/scale-gate.yml, .github/workflows/perf-gate.yml and 10 more · reported by agent-audit-kit
1 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-DNS-REBIND-001 · Files: integrations/perseus-vault-persist/tests/test_event_store.py · reported by agent-audit-kit
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.
31 PIPELINE_TAINT_FLOW
Files: /repo/ROADMAP.md, /repo/SKILL.md, /repo/scripts/bootstrap.sh and 15 more · reported by cisco-skill-scanner
30 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/benchmark/contention/live_bench.py, /repo/benchmark/lambda/parallel_embed.py, /repo/benchmark/lambda/parallel_embed_fleet.py and 2 more · reported by cisco-skill-scanner
30 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/benchmark/lambda/campaign_run.sh, /repo/benchmark/lambda/coldstart_capture.sh, /repo/benchmark/lambda/gate.sh and 3 more · reported by cisco-skill-scanner
25 MANIFEST_MISSING_LICENSE
Files: /repo/clawhub/skills/mimir/SKILL.md, /repo/SKILL.md, /repo/benchmark/SKILL.md and 22 more · reported by cisco-skill-scanner
24 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/benchmark/contention/burn_bench.py, /repo/benchmark/lambda/competitors_bench.py, /repo/benchmark/lambda/rag_bench.py and 6 more · reported by cisco-skill-scanner
Artifact exhibits critical shell execution, system modification, and network access capabilities.
The artifact contains numerous critical findings related to shell execution and system modification, particularly within shell scripts in the `benchmark/lambda` directory. It also includes capabilities for fetching and executing external code, as seen in `provision.sh`, and potential path traversal in `build_report.py`. Further critical findings indicate potential server-side request forgery in `benchmark/lambda/scale_bench_1m.py` and DNS rebinding in `integrations/perseus-vault-persist/perseus_vault_persist/store.py`.
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.
24 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/benchmark/SKILL.md, /repo/benchmarks/SKILL.md and 21 more · reported by cisco-skill-scanner
11 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/ROADMAP.md, /repo/clawhub/skills/mimir/SKILL.md and 8 more · reported by nerlo-install-instruction
10 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/clawhub/skills/mimir/SKILL.md, /repo/integrations/README.md and 7 more · reported by nerlo-install-instruction
9 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/benchmark/lambda/competitors_bench.py, /repo/benchmark/lambda/offline_bench.py · reported by cisco-skill-scanner
8 AAK-SECRET-004
Files: src/encryption.rs, src/embedding.rs, src/grpc.rs and 3 more · reported by agent-audit-kit
5 AAK-TAINT-002
Files: src/mcp.rs · reported by agent-audit-kit
5 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/benchmark/repo/benchmark/GAUNTLET.md, /repo/benchmark/lambda/repo/benchmark/lambda/README.md and 2 more · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/obsidian-mimir/main.ts · reported by cisco-skill-scanner
4 COMPOUND_FETCH_EXECUTE
Files: /repo/benchmark/lambda/provision.sh, /repo/scripts/bootstrap.sh · reported by cisco-skill-scanner
4 HIDDEN_DATA_FILE
Files: /repo/.well-known/funding-manifest-urls, /repo/.hermes/plans/discord-scout-impl.md, /repo/.well-known/mcp/server-card.json and 1 more · reported by cisco-skill-scanner
3 BINARY_FILE_DETECTED
Files: /repo/benchmark/scale/fresh-scale-2026-07-12.log · reported by cisco-skill-scanner
3 COMMAND_INJECTION_OS_SYSTEM
Files: /repo/benchmark/lambda/quality_lift.py · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/plugins/obsidian-mimir/main.ts · reported by nerlo-behavioral
3 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/benchmark/lambda/competitors_bench.py, /repo/benchmark/lambda/offline_bench.py, /repo/benchmark/lambda/quality_lift.py · reported by nerlo-behavioral
3 PATH_TRAVERSAL_OPEN
Files: /repo/benchmark/lambda/build_report.py · reported by cisco-skill-scanner
3 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/benchmark/lambda/provision.sh · reported by cisco-skill-scanner
3 UNANALYZABLE_BINARY
Files: /repo/benchmark/scale/fresh-scale-2026-07-12.log · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: FABLE5-HANDOFF.md, benchmark/longmemeval/SUPERSEDE_590.md · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/benchmark/. · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/benchmark/contention/live_bench.py, /repo/benchmark/longmemeval/qa.py · reported by nerlo-behavioral
1 AAK-DNS-REBIND-001
Files: integrations/perseus-vault-persist/perseus_vault_persist/store.py · reported by agent-audit-kit
1 AAK-MCP-018
Files: integrations/perseus-vault-persist/perseus_vault_persist/store.py · reported by agent-audit-kit
1 AAK-SKILL-001
Files: clawhub/skills/mimir/SKILL.md · reported by agent-audit-kit
1 AAK-SSRF-001
Files: benchmark/lambda/scale_bench_1m.py · reported by agent-audit-kit
1 AAK-SSRF-002
Files: benchmark/lambda/scale_bench_1m.py · reported by agent-audit-kit
1 AAK-SSRF-005
Files: benchmark/lambda/scale_bench_1m.py · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 COMPOUND_FIND_EXEC
Files: /repo/scripts/build-mcpb.sh · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/benchmark/scale · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/benchmark/shared_scale/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md · reported by nerlo-install-instruction
Showing 25 of 128; the rest are in the per-scanner reports above.