Bring affiliate-network data to Claude or Codex through a local stdio MCP server. 80+ publisher and advertiser-side adapters, most experimental. Local-only, bring your own keys.
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.
149 critical findings reported by agent-audit-kit, 10 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/bobberrisford/affiliatemcp, 425 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- affiliate-networks-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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
2 findings · 7.2s
v2.0.11
Timed out
0 findings · 300.0s
v0.3.26
286 findings · 189.9s
v0.1.0
137 findings · 255.7s
v0.1.0
0 findings · 255.8s
v0.1.0
0 findings · 74.8s
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: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 29, 2026 | Scan Halted | — | cisco-skill-scanner ·!: timeoutagent-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 425 findings across every scanner that examined this package. 138 of 149 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.
137 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 · Files: AGENTS.md, CLAUDE.md · reported by agent-audit-kit
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-HEALTHCARE-AI-005, AAK-HEALTHCARE-AI-004, AAK-SECRET-007 · Files: docs/decisions/2026-07-17-telemetry-and-containers-ci-deploy.md, docs/networks/admitad.md, docs/networks/adtraction.md and 19 more · reported by agent-audit-kit
18 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-INDIA-PII-001, AAK-SECRET-004, AAK-OAUTH-002 and 2 more · Files: tests/fixtures/rewardful/commissions.json, tests/tools/generate.test.ts, tests/networks/awin-advertiser/tools.test.ts and 11 more · 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.
116 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/hosted/src/auth-link.ts, /repo/hosted/src/connect-test.ts, /repo/hosted/src/digest.ts and 93 more · reported by nerlo-behavioral
66 AAK-SECRET-004
Files: src/networks/everflow/auth.ts, src/networks/involve-asia/auth.ts, src/networks/impact-advertiser/auth.ts and 41 more · reported by agent-audit-kit
21 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/desktop/main.js, /repo/hosted/src/auth-link.ts, /repo/hosted/src/connect-test.ts and 15 more · reported by nerlo-behavioral
14 AAK-OAUTH-005
Files: src/hosted-transport/http-server.ts, src/networks/hotmart/client.ts, src/networks/admitad/client.ts and 11 more · reported by agent-audit-kit
7 AAK-INDIA-PII-001
Files: src/networks/involve-asia/auth.ts, src/networks/involve-asia/client.ts, src/networks/involve-asia/adapter.ts and 3 more · reported by agent-audit-kit
Artifact has critical command injection and sensitive data handling risks.
The artifact contains a critical command injection vulnerability in `src/server.ts`, allowing for shell execution. It also handles sensitive PII in multiple network adapters, including `src/networks/flexoffers/adapter.ts` and `src/networks/involve-asia/adapter.ts`. Additionally, the artifact has numerous instances of potential credential access and network egress, particularly in `hosted/src/connect-test.ts` and `src/networks/addrevenue/adapter.ts`.
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.
3 AAK-MCP-STATELESS-001
Files: containers/src/index.ts, src/hosted-transport/http-server.ts, src/hosted-transport/stateless-handler.ts · reported by agent-audit-kit
2 AAK-ANTHROPIC-SDK-001
Files: scripts/smoke-mcp.mjs, src/server.ts · reported by agent-audit-kit
2 AAK-HEALTHCARE-AI-004
Files: CODE_OF_CONDUCT.md, skills/affiliate-network-setup-help/SKILL.md · reported by agent-audit-kit
2 AAK-STATE-PRIVACY-001
Files: PRIVACY.md, site/privacy.html · reported by agent-audit-kit
2 AAK-STATE-PRIVACY-002
Files: PRIVACY.md, site/privacy.html · reported by agent-audit-kit
2 AAK-STATE-PRIVACY-003
Files: PRIVACY.md, site/privacy.html · reported by agent-audit-kit
2 AAK-TAINT-001
Files: scripts/conformance-hosted.ts, scripts/hosted-capture-token.ts · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: telemetry-cloudflare/package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: scripts/conformance-hosted.ts · reported by agent-audit-kit
1 AAK-MCP-STDIO-CMD-INJ-002
Files: src/server.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SKILL-003
Files: .claude/skills/contribute/SKILL.md · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 skills-missing-governance-skills/README.md
Files: skills/README.md · reported by agentshield
1 skills-missing-telemetry-skills/README.md
Files: skills/README.md · reported by agentshield
Showing 25 of 199; the rest are in the per-scanner reports above.