Loading the registry…
GFT (Git for Thought) MCP server — bring your white-box thinking map to any AI agent. 把你在 GFT 确认过的思维脉络接给任何 agent:用它们的 token,走 GFT 的规则。
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.
2 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/CoralLips/gft-mcp, 13 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- gft-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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
0 findings · 0.4s
v2.0.11
6 findings · 6.1s
v0.3.26
7 findings · 0.6s
v0.1.0
0 findings · 27.1s
v0.1.0
0 findings · 27.1s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 10, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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 13 findings across every scanner that examined this package. None of the 2 findings rated critical by their scanner were dismissed.
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.
2 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/plugin/commands/SKILL.md · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: server.mjs · reported by agent-audit-kit
1 AAK-DNS-REBIND-002
Files: package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-STDIO-CMD-INJ-002
Files: server.mjs · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: server.mjs · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugin/hooks/gft-hook.js · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 SECRET_JWT_TOKEN
Files: /repo/server.mjs · reported by cisco-skill-scanner
1 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md · reported by cisco-skill-scanner
Artifact allows shell execution and credential access.
Critical findings indicate the artifact can execute shell commands via child processes in `server.mjs` and `/repo/plugin/hooks/gft-hook.js`. High severity findings show potential for credential access, specifically a JWT token in `/repo/server.mjs`. The artifact also interacts with an Anthropic SDK and a marketplace, and has a DNS rebind vulnerability in `package.json`.
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.