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.
152 critical findings reported by cisco-skill-scanner, agent-audit-kit, 25 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 -- emem
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
332 findings · 63.7s
v0.3.26
184 findings · 43.3s
v0.1.0
13 findings · 35.6s
v0.1.0
0 findings · 35.6s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 11.5s
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 ·n/a: not applicable | rejected |
| Aug 1, 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 |
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 529 findings across every scanner that examined this package. 126 of 152 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.
223 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-INDIA-PII-001, YARA_command_injection_generic, AAK-MCP-001 and 21 more · Files: examples/3d-worlds/scenes/canyon.scene.json, examples/3d-worlds/scenes/interlaken.scene.json, /repo/docs/operators/operating.md and 60 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-behavioral
80 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, AAK-AGENT-002 · Files: AGENTS.md · reported by agent-audit-kit
12 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/publish-pypi.yml, .github/workflows/publish-pypi-langmem.yml and 2 more · reported by agent-audit-kit, cisco-skill-scanner
8 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_EVAL, AAK-HEALTHCARE-AI-005, MANIFEST_INVALID_NAME · Files: /repo/python/jepa_v2_sidecar/test_galileo_norm.py, tests/comprehensive/questions_v2.json, tests/comprehensive/results/climate_worry_report.md and 4 more · reported by cisco-skill-scanner, 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.
44 HIDDEN_DATA_FILE
Files: /repo/.well-known/agent-notes/README.md, /repo/.well-known/agent-notes/AGENT_NOTE_110_live.md, /repo/.well-known/agent-notes/AGENT_POINTER_contacts_registry_2026-07-19.md and 41 more · reported by cisco-skill-scanner
28 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/bench/corpus.py, /repo/bench/record_run.py, /repo/scripts/agent_ack.py and 8 more · reported by cisco-skill-scanner
24 COMMAND_INJECTION_EVAL
Files: /repo/python/jepa_v2/export_baseline.py, /repo/python/jepa_v2/train.py, /repo/python/jepa_v2_sidecar/server.py and 1 more · reported by cisco-skill-scanner
20 MANIFEST_MISSING_LICENSE
Files: /repo/claude-skills/emem-a2a-collaboration/SKILL.md, /repo/claude-skills/emem-find-similar/SKILL.md, /repo/claude-skills/emem-verify-receipt/SKILL.md and 17 more · reported by cisco-skill-scanner
16 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/claude-skills/emem-sign-and-attest/SKILL.md, /repo/claude-skills/emem-field-tokens/SKILL.md, /repo/SKILL.md and 13 more
The model could have called any of these a false positive and did not.
14 AAK-SECRET-004
Files: examples/benchmark-arm/differential_scorer.py, examples/3d-worlds/three.min.js, sdks/emem-langmem/tests/test_signing.py and 4 more · reported by agent-audit-kit
Critical risks: command injection, credential harvesting, and secret exposure.
The artifact contains multiple critical command injection vulnerabilities, primarily within Python files like `/repo/python/jepa_v2/export_baseline.py`, `/repo/python/jepa_v2/train.py`, and `/repo/python/jepa_v2_sidecar/server.py`. It also exhibits a critical credential harvesting pattern in `/repo/crates/emem-cli/src/bin/emem-server.rs`. Additionally, there are high-severity findings related to potential secret exposure and network egress of secrets.
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.
14 AAK-SECRET-004
Files: scripts/gen_protocol.py, web/data/relay-recording.json, scripts/eval/physics/wave_mumbai.json and 10 more · reported by agent-audit-kit
4 ARCHIVE_FILE_DETECTED
Files: /repo/crates/emem-fetch/data/admin1CodesASCII.txt.gz, /repo/crates/emem-fetch/data/countryInfo.txt.gz, /repo/crates/emem-fetch/data/admin2Codes.txt.gz and 1 more · reported by cisco-skill-scanner
4 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/python/jepa_v2/repo/python/jepa_v2/README.md, /repo/python/jepa_v2_sidecar/repo/python/jepa_v2_sidecar/README.md, /repo/sdks/emem-langmem/repo/sdks/emem-langmem/README.md and 1 more · reported by cisco-skill-scanner
4 TOOL_ABUSE_UNTRUSTED_PACKAGE_SOURCE
Files: /repo/python/jepa_v2_sidecar/server.py · reported by cisco-skill-scanner
4 UNANALYZABLE_BINARY
Files: /repo/crates/emem-fetch/data/countryInfo.txt.gz, /repo/crates/emem-fetch/data/admin2Codes.txt.gz, /repo/crates/emem-fetch/data/admin3Codes.txt.gz and 1 more · reported by cisco-skill-scanner
3 AAK-STATE-PRIVACY-002
Files: PRIVACY.md, TERMS.md, integrations/chatgpt/privacy.md · reported by agent-audit-kit
3 AAK-STATE-PRIVACY-003
Files: PRIVACY.md, TERMS.md, integrations/chatgpt/privacy.md · reported by agent-audit-kit
3 MANIFEST_INVALID_NAME
Files: /repo/python/jepa_v2_sidecar/SKILL.md, /repo/python/gemma_explain/SKILL.md, /repo/python/jepa_v2/SKILL.md · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: .well-known/agent-notes/AGENT_HANDOFF_world_models.md, .well-known/agent-notes/AGENT_REPLY_world_models.md · reported by agent-audit-kit
2 AAK-STATE-PRIVACY-001
Files: TERMS.md, integrations/chatgpt/privacy.md · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/sdks/emem-ts/src/client.ts · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/web/llms.txt · reported by cisco-skill-scanner
2 YARA_prompt_injection_unicode_steganography
Files: /repo/web/logo-1200w.png · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-005
Files: crates/emem-core/data/bands-v0.json · reported by agent-audit-kit
1 AAK-SKILL-001
Files: claude-skills/emem-verify-receipt/SKILL.md · reported by agent-audit-kit
1 AAK-SKILL-005
Files: claude-skills/emem-a2a-collaboration/SKILL.md · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 ALLOWED_TOOLS_READ_VIOLATION
Files: /repo/claude-skills/emem-verify-receipt/repo/claude-skills/emem-verify-receipt/SKILL.md · reported by cisco-skill-scanner
1 ALLOWED_TOOLS_WRITE_VIOLATION
Files: /repo/claude-skills/emem-verify-receipt/repo/claude-skills/emem-verify-receipt/SKILL.md · reported by cisco-skill-scanner
1 COMPOUND_EXTRACT_EXECUTE
Files: /repo/scripts/mcp-publish.sh · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/sdks/emem-ts · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/scripts/record_relay.py · reported by nerlo-behavioral
1 YARA_credential_harvesting_generic
Files: /repo/crates/emem-cli/src/bin/emem-server.rs · reported by cisco-skill-scanner
Showing 25 of 62; the rest are in the per-scanner reports above.