helios@1.8.7
CAUTION· not startedPublisher claims: "Enables AI coding agents to persist atomic, token-budgeted facts across sessions via SQLite-backed full-text search, automatically superseding outdated entries and flagging memories as stale when Git webhooks detect changes to anchored repo files." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
HELIOS_API_KEYHELIOS_REQUIRE_WEBHOOK_SECRETHELIOS_WEBHOOK_SECRETWEBHOOK_SECRETConfiguration, not credentials: GEMINI_PATH, HELIOS_ALLOWED_ORIGINS, HELIOS_AUTO_SEED, HELIOS_CORS_ORIGINS, HELIOS_GIT_API_URL, HELIOS_GIT_PROVIDER, HOOKS_PATH, MEMORY_DATA_DIR- Where it talks to
- no vendor host named in the codeAlso opencode.ai — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names opencode.ai as well as its own vendor. The guard injects HELIOS_API_KEY, HELIOS_REQUIRE_WEBHOOK_SECRET, HELIOS_WEBHOOK_SECRET, WEBHOOK_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.
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 ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Access to sensitive file paths; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
f" curl -fsSL {clean_base}/setup.sh{token_suffix} | bash\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Usage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chown -R helios:helios /data /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Usage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.data['mcpServers']['helios'] = {{'url': sse_url}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.f"> - Linux/macOS: `curl -fsSL {resolved_base}/uninstall.sh | bash` (or append `?client={client}`)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.$claudeData.mcpServers["helios"] = @{{ command = "npx"; args = @("-y", "mcp-remote", $sseUrl) }}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."Configure the following in your Helios `.env` and restart Helios:\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Usage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chmod +x "$SCRIPTS_DIR/helios_guard.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Usage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Usage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f" curl -fsSL {clean_base}/setup.sh{token_suffix} | bash\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f"> - Linux/macOS: `curl -fsSL {resolved_base}/uninstall.sh | bash` (or append `?client={client}`)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.$cursorData.mcpServers["helios"] = @{{ url = $sseUrl }}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.validate_http_url("https://user:[email protected]")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.validate_http_url("http://169.254.169.254/latest/meta-data")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert "curl -fsSL https://helios.mesh.net/uninstall.sh | bash" in res_ui.textFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.data['mcpServers']['helios'] = {{'command': 'npx', 'args': ['-y', 'mcp-remote', sse_url]}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."http://user:[email protected]/api", # Credentials in URLFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.….mdc`), Claude Desktop (`claude_desktop_config.json`), Claude Code (`claude mcp add` + `~/.claude/CLAUDE.md`), OpenAI Codex (`~/.codex/config.toml` + `~/.codex/AGENTS.md`), Windsurf (`~/.codeium/windsurf/mcp_config.json` + `memories/global…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Usage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."http://0x7f000001/", # Hex representation of 127.0.0.1Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.…01887b3edff)) ## [1.2.0] - 2026-10-26 ### Features - **Onboarding**: Enforce Write-Through Definition of Done (DoD) in global client directives (`GEMINI.md`, `CLAUDE.md`, `.cursor/rules/helios.mdc`) and `/remember` skill across all support…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."http://169.254.169.254/latest/meta-data",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."http://100.100.100.200/metadata",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Usage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Usage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert "curl -fsSL https://helios.mesh.net/uninstall.sh | bash" in res_ui.textFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert validate_http_url("http://192.168.1.50:8000") == "http://192.168.1.50:8000"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."http://100.100.100.200/metadata",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim brazaoo4: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.