Loading the registry…
Local-first, source-grounded memory for AI agents with citations, bitemporal history, and MCP.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
4 critical findings reported by cisco-skill-scanner, agent-audit-kit, 1 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github_release: https://github.com/ampres-ai/talamus, 0 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- talamus
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 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
64 findings · 15.4s
v0.3.74
45 findings · 19.0s
v0.2.0
2 findings · 38.7s
v0.2.0
0 findings · 38.7s
v0.1.0
0 findings · 152.6s
v0.71.0
0 findings · 0.4s
v2.3.8
4 findings · 7.8s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
5 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 22, 2026 | Flagged63 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Sep 3, 2026 | Flagged65 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Aug 2, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 28, 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 115 findings across every scanner that examined this package. 3 of 4 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.
22 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-STATE-PRIVACY-002, AAK-STATE-PRIVACY-001, YARA_prompt_injection_unicode_steganography and 5 more · Files: docs/privacy.md, docs/terms.md, /repo/docs/assets/talamus-demo.gif and 7 more · reported by agent-audit-kit, cisco-skill-scanner
12 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-004, AAK-ANTHROPIC-SDK-001 and 4 more · Files: tests/test_talamus_redact.py, tests/test_talamus_cli.py, tests/test_talamus_mcp_server.py and 5 more · reported by agent-audit-kit, cisco-skill-scanner
3 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/container.yml · 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.
12 AAK-SECRET-004
Files: src/talamus/noteparse.py, src/talamus/adapters/llm.py, src/talamus/webapi/app.py and 2 more · reported by agent-audit-kit
12 HIDDEN_DATA_FILE
Files: /repo/.agents/skills/talamus-memory/SKILL.md, /repo/.agents/skills/talamus-memory/agents/openai.yaml, /repo/.goose-plugin/plugin.json and 6 more · reported by cisco-skill-scanner
10 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/openai/talamus-memory/skills/talamus-memory/SKILL.md, /repo/plugins/talamus-memory/skills/talamus-memory/SKILL.md, /repo/plugins/talamus-memory/cursor-skills/talamus-memory/SKILL.md and 7 more · reported by cisco-skill-scanner
6 AAK-MCP-007
Files: plugins/talamus-memory/.mcp.json, plugins/talamus-memory/.goose-mcp.json · reported by agent-audit-kit
6 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/webui/SKILL.md, /repo/benchmarks/SKILL.md and 3 more · reported by cisco-skill-scanner
Critical command injection and credential exposure risks
The artifact contains a critical command injection vulnerability in `/repo/src/talamus/services/diagnostics.py`, enabling shell execution. Multiple instances of credential exposure are identified, including in `benchmarks/ask_eval/judges.py`, `src/talamus/adapters/llm.py`, and several `src/talamus/webapi/static/assets/index-BFHM89ps.js` files. Network egress of secrets is also noted in `/repo/webui/src/api.ts`, alongside high-severity vulnerabilities in dependencies. An infinite loop condition in `/repo/src/talamus/watch.py` could lead to resource abuse.
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.
5 DATA_EXFIL_JS_NETWORK
Files: /repo/src/talamus/webapi/static/assets/index-BFHM89ps.js, /repo/webui/src/api.ts · reported by cisco-skill-scanner
4 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/talamus/adapters/llm.py, /repo/src/talamus/sources.py · reported by cisco-skill-scanner
2 AAK-MCP-005
Files: plugins/talamus-memory/.mcp.json, plugins/talamus-memory/.goose-mcp.json · reported by agent-audit-kit
2 AAK-MCP-ATTEST-001
Files: plugins/talamus-memory/.mcp.json, plugins/talamus-memory/.goose-mcp.json · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/webui/src/api.ts · reported by nerlo-behavioral
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/benchmarks/repo/benchmarks/README.md · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: scripts/smoke_mcp_stdio.py · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: webui/package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .cursor-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: scripts/build_smithery_mcpb.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TASKS-003
Files: src/talamus/routing.py · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/src/talamus/services/diagnostics.py · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 GHSA-2v37-7h3g-55p8
Files: /repo/webui/package-lock.json · reported by osv-scanner
1 GHSA-73wf-gq98-2v4g
Files: /repo/webui/package-lock.json · reported by osv-scanner
1 GHSA-c83g-rgw3-j3cx
Files: /repo/webui/package-lock.json · reported by osv-scanner
1 GHSA-w5vr-8v7q-w6rv
Files: /repo/webui/package-lock.json · reported by osv-scanner
1 LOW_ANALYZABILITY
Files: /repo/webui · reported by cisco-skill-scanner
1 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/src/talamus/watch.py · reported by cisco-skill-scanner
1 YARA_autonomy_abuse_generic
Files: /repo/src/talamus/ingest.py · reported by cisco-skill-scanner