rollback-mcp@0.2.0
CAUTION· static onlyPublisher claims: "A reversibility layer for agentic tool use — a transparent MCP proxy that classifies which tool calls can be taken back, synthesises inverse operations, keeps a durable cross-server undo log, and interrupts you only for genuinely irreversible actions." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
One line in ``mcp.json`` puts Unwind transparently in front of any stdio MCPFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.<summary><b>Cline</b> · <code>cline_mcp_settings.json</code></summary> ```json { "mcpServers": { "filesystem": { "command": "unwind", "args": ["run"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>VS Code</b> (MCP) · <code>.vscode/mcp.json</code></summary> ```json { "servers": { "filesystem": { "command": "unwind", "args": ["run", Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Goose</b> · <code>~/.config/goose/config.yaml</code></summary> ```yaml extensions: filesystem: type: stdio cmd: unwind args: ["run", "--Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Cursor</b> · <code>~/.cursor/mcp.json</code></summary> ```json { "mcpServers": { "filesystem": { "command": "unwind", "args": ["run", "-Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.``npx -y @modelcontextprotocol/server-filesystem /path`` → ``server-filesystem``Fix: Pin versions and sources; vendor anything fetched at install time.<summary><b>Windsurf</b> · <code>~/.codeium/windsurf/mcp_config.json</code></summary> ```json { "mcpServers": { "filesystem": { "command": "unwind",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Claude Code</b> · <code>.mcp.json</code></summary> ```json { "mcpServers": { "filesystem": { "command": "unwind", "args": ["run", "--", Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.coverage.xml .coverage output.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."upstream command and args (put after `--`), e.g. -- npx -y @modelcontextprotocol/server-filesystem /path",Fix: Pin versions and sources; vendor anything fetched at install time.npx -y @modelcontextprotocol/server-filesystem /workFix: Pin versions and sources; vendor anything fetched at install time.* rollback-mcp run -- npx -y @modelcontextprotocol/server-filesystem /pathFix: Pin versions and sources; vendor anything fetched at install time.<summary><b>Zed</b> · <code>settings.json</code></summary> ```json { "context_servers": { "filesystem": { "command": { "path": "unwind", "args": ["rFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.autoupdate_commit_msg: "chore(pre-commit): autoupdate hook versions"Fix: Pin versions and sources; vendor anything fetched at install time.<summary><b>Claude Desktop</b> · <code>claude_desktop_config.json</code></summary> ```json { "mcpServers": { "filesystem": { "command": "unwind", "aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim bhaskargurram-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.