Build agent applications with typed chat, tools, sandboxes, integrations, billing, and evaluation.
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.
43 critical findings reported by cisco-skill-scanner, 13 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
npm: @tangle-network/agent-app @ 0.46.55, 0 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @tangle-network/agent-app
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
8 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.
v1.4.0
4 findings · 1.1s
v2.0.11
210 findings · 35.7s
v0.3.74
48 findings · 40.2s
v0.1.0
8 findings · 55.6s
v0.1.0
3 findings · 55.7s
v0.1.0
0 findings · 61.0s
v0.71.0
0 findings · 1.0s
v2.3.8
0 findings · 8.7s
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
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 5, 2026 | Flagged74 | — | agentshield: completecisco-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 | Flagged78 | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicable | completed |
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 273 findings across every scanner that examined this package. 30 of 43 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 6 findings 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.
112 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, YARA_command_injection_generic, AAK-SECRET-004 and 12 more · Files: /repo/create-agent-app/template-chat/tests/chat-turn.e2e.test.ts, /repo/src/store/index.test.ts, /repo/tests/chat-routes/promote-file-part.test.ts and 44 more · reported by cisco-skill-scanner, agent-audit-kit
12 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FILE_MAGIC_MISMATCH, EXCESSIVE_FILE_COUNT, SOCIAL_ENG_VAGUE_DESCRIPTION and 2 more · Files: /repo/docs/llms.txt, /repo/docs/llms-full.txt, /repo/docs/. and 4 more · reported by cisco-skill-scanner, nerlo-install-instruction
11 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: COMMAND_INJECTION_JS_CHILD_PROCESS, COMPOUND_EXTRACT_EXECUTE, DATA_EXFIL_JS_FS_ACCESS · Files: /repo/.github/scripts/test-generated-projects.mjs, /repo/.github/scripts/test-publish-workflow.mjs, /repo/src/signoff/run.test.ts and 4 more · reported by cisco-skill-scanner
10 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-003, AAK-AGENT-002, agents-prompt-extraction-85361 and 4 more · Files: AGENTS.md, CLAUDE.md, /repo/AGENTS.md and 1 more · reported by agent-audit-kit, agentshield, nerlo-install-instruction
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.
37 DATA_EXFIL_JS_NETWORK
Files: /repo/create-agent-app/template-chat/src/worker.ts, /repo/create-agent-app/template/src/worker.ts, /repo/src/assistant/client.ts and 16 more · reported by cisco-skill-scanner
14 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/measurement-validation/SKILL.md, /repo/.claude/skills/skill-evolution/SKILL.md, /repo/.claude/skills/eval-architect/SKILL.md and 11 more · reported by cisco-skill-scanner
9 COMMAND_INJECTION_EVAL
Files: /repo/src/integrations/index.ts, /repo/src/sandbox/binary-read.ts, /repo/src/sandbox/index.ts and 3 more · reported by cisco-skill-scanner
8 AAK-OAUTH-007
Files: src/tangle/index.ts, src/work-product/route.ts, src/chat-routes/upload.ts and 5 more · reported by agent-audit-kit
8 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/assistant/client.ts, /repo/src/runtime/model-catalog.ts, /repo/src/web-react/message-attachments.tsx
The model could have called any of these a false positive and did not.
1 LOW_ANALYZABILITY
Files: /repo/examples · reported by cisco-skill-scanner
6 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/create-agent-app/template/.dev.vars.example, /repo/create-agent-app/template-chat/.dev.vars.example · reported by cisco-skill-scanner
Critical command injection and secret exposure risks identified.
The artifact contains critical command injection vulnerabilities in multiple files, including those related to evaluation and child process execution. It also exhibits high-severity risks involving network egress of secrets and potential OAuth credential exposure. These findings indicate capabilities for shell execution, credential access, and network communication.
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.
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/eval-bootstrap/SKILL.md, /repo/SKILL.md, /repo/create-agent-app/SKILL.md and 5 more · reported by cisco-skill-scanner
7 AAK-OAUTH-001
Files: src/work-product/route.ts, src/chat-routes/upload.ts, src/chat-routes/attachment-upload.ts and 4 more · reported by agent-audit-kit
6 AAK-SECRET-004
Files: src/redact/index.ts, src/runtime/model.ts, src/sandbox/diagnostics.ts and 2 more · reported by agent-audit-kit
6 FILE_MAGIC_MISMATCH
Files: /repo/create-agent-app/template-chat/src/worker.ts, /repo/src/turn-health/index.ts, /repo/src/sandbox/diagnostics.ts and 1 more · reported by cisco-skill-scanner
5 LOW_ANALYZABILITY
Files: /repo, /repo/create-agent-app/template, /repo/playground and 2 more · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/src/signoff/proof-git.ts, /repo/src/signoff/proof-record.ts, /repo/src/signoff/run.ts and 1 more · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/skills/index.ts · reported by cisco-skill-scanner
2 YARA_autonomy_abuse_generic
Files: /repo/src/missions/engine.ts · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: playground/package.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 YARA_code_execution_generic
Files: /repo/src/model-resolution/failover.ts · reported by cisco-skill-scanner
Showing 25 of 34; the rest are in the per-scanner reports above.