ToolTrust
B15/100
iflytek

astron-agent

mcp1.0.9

@iflytek

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

By iflytek | 32 findings | Scanned 10/15/2026 | tooltrust-scanner/v0.3.20 | 8.9k

Repository health

Popularity and maintenance signals alongside the security grade.

View repository
Stars

8.9k

current snapshot

Forks

909

current snapshot

Contributors

61

public GitHub contributors

Last commit

Oct 28, 2026

GitHub repository activity

Last release

Sep 7, 2026

Astron Agent v1.1.2 — Security Release

Release version

v1.1.2

Latest GitHub release

Stars trend

Daily star additions · githubarchive_bq · observed through Oct 29, 2026 · export updated Oct 29, 2026

17d
2026-07-182026-10-28

Pull request activity

Weekly PR events · githubarchive_bq · observed through Oct 29, 2026 · export updated Oct 29, 2026

2026-08-032026-09-07

Data quality: observed_events. Charts show observed events, not a reconstructed historical total.

JavaApache-2.0OtherLast scan Oct 15, 2026
1 High2 Low29 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (32)

  • HighAS-012

    🔄Tool Drift

    Tool set changed silently at v1.0.9: 13 tool(s) added, 4 tool(s) removed without a version bump.

    + 13 added

    relay_ack_approvalrelay_channel_inforelay_create_channelrelay_create_taskrelay_join_channelrelay_leave_channelrelay_list_approvalsrelay_list_messagesrelay_register_agentrelay_request_approvalrelay_respond_approvalrelay_send_messagerelay_wait_message

    − 4 removed

    get_catalog_infoget_vendorlookup_vendorsreport_to_outpost

    Fix: The set of tools exposed by this server changed between scans of the same version — a sign the package was silently updated without a version bump. Audit the changelog and all tool definitions before trusting this server. Pin to a specific commit hash rather than a floating version tag.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×2

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    relay_request_approvalrelay_list_approvals

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×13

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    relay_register_agentrelay_create_channelrelay_join_channelrelay_send_messagerelay_create_taskrelay_list_messagesrelay_wait_messagerelay_request_approvalrelay_respond_approvalrelay_leave_channelrelay_list_approvalsrelay_ack_approvalrelay_channel_info

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×4

    declared capabilities: filesystem access

    relay_create_channelrelay_create_task

    declared capabilities: network access

    relay_request_approvalrelay_list_approvals

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-010

    🔑Insecure Secret Handling ×12

    input parameter "secret" accepts a credential (informational; not evidence of insecure handling)

    relay_create_channelrelay_join_channelrelay_send_messagerelay_create_taskrelay_list_messagesrelay_wait_messagerelay_request_approvalrelay_leave_channelrelay_list_approvalsrelay_ack_approvalrelay_channel_info

    input parameter "humanToken" accepts a credential (informational; not evidence of insecure handling)

    relay_respond_approval

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y astron-agent"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade B](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-b.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)