registry / @finchagentic/mcp / 4.7.1
@finchagentic/mcp@4.7.1
The runtime layer for Agentic AI. Persistent memory, autonomous agents, and workflows that survive every session.
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged credential flows use provider-specific endpoints consistent with this agent package, while the custom endpoint requires user input in setup. The reviewed manifest has no install hooks, and I found no evidence of unrelated automatic credential exfiltration.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
LLM requests run when the agent or an LLM-backed tool is used; custom routing is configured through the interactive finch setup command.
Impact
The inspected behavior matches the package’s agent and LLM functionality; no unrelated credential destination was found.
Mechanism
Provider keys are sent to their corresponding LLM endpoint. The custom endpoint URL is entered by the user during setup.
AI rationale
The flagged credential flows use provider-specific endpoints consistent with this agent package, while the custom endpoint requires user input in setup. The reviewed manifest has no install hooks, and I found no evidence of unrelated automatic credential exfiltration.
Evidence
package.jsondist/cli.jsdist/agent-loop.jsdist/llm.js
Network endpoints4
api.anthropic.comapi.openai.comapi.x.aillm.bankr.bot
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest routes the package entrypoints to dist/index.js and the finch command to dist/cli.js; it declares no install lifecycle hooks.
- LLM credentials are selected for provider calls, and the Anthropic agent loop sends its key to api.anthropic.com.
- The custom OpenAI-compatible endpoint and its API key are collected through an explicit setup choice, and the CLI says requests will route to the entered URL.
- Bankr credentials are sent to the declared Bankr endpoint.
Evidence against
- The package provides an autonomous agent and LLM tools, so provider API calls are consistent with its purpose.
- No reviewed credential flow showed an unrelated fixed destination or automatic install-time collection.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
6 flaggeddist/local-vault.jsView file
68// vault handlers already catch and format that).
L69: const VAULT_DIR = path.join(os.homedir(), ".finch", "vault");
L70: // Local vault is enabled purely by config - it needs no server, just the
...
L89: const raw = fs.readFileSync(indexPath(cfg), "utf8");
L90: const parsed = JSON.parse(raw);
L91: return { entries: parsed.entries ?? {}, links: parsed.links ?? [] };
...
L175: agentId: input.agentId, tags, pinned: false, currentVersion: 1,
L176: createdAt: ts, updatedAt: ts, metadata: input.metadata,
L177: versions: [{ version: 1, commitMsg: input.commitMsg, agentId: input.agentId, size: Buffer.byteLength(input.content), createdAt: ts }],
Low
Weak Crypto
Package source references weak cryptographic algorithms.
dist/local-vault.jsView on unpkg · L68dist/agent-loop.jsView file
30async function runAgent(userMessage, history, onToolCall) {
L31: const provider = process.env.FINCH_PROVIDER?.toLowerCase().trim();
L32: const bankrKey = process.env.BANKR_API_KEY;
...
L144: const sendTurn = async (messages, tools) => {
L145: const res = await fetch("https://api.anthropic.com/v1/messages", {
L146: method: "POST",
...
L151: },
L152: body: JSON.stringify({ model, max_tokens: 4096, system: SYSTEM_PROMPT, tools, messages }),
L153: signal: AbortSignal.timeout(90000),
...
L155: if (!res.ok) {
L156: const body = await res.text().catch(() => "");
L157: throw new Error(`Anthropic ${res.status}: ${body.slice(0, 300)}`);
Findings
1 Critical4 High2 Medium5 Low
CriticalPrevious Version Dangerous Deltadist/server.js
HighCredential Exfiltrationdist/agent-loop.js
HighCredential Redirect Persistencedist/cli.js
HighTrigger Reachable Credential Exfiltrationdist/agent-loop.js
HighSemantic Analysis Limiteddist/agent-loop.js#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
LowScripts Present
LowWeak Cryptodist/local-vault.js
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @finchagentic/mcp@4.7.1.
See all versions of @finchagentic/mcp for other recorded verdicts.
- Review the evidence and your use of @finchagentic/mcp@4.7.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.