Skills/Glama/helios

helios@1.8.7

CAUTION· not started

Publisher 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to persist atomic, token-budgeted facts across sessions via SQLite-backed full-text search, automatically superseding outdated entries and flagging memories as stale when Git webhooks detect changes to anchored repo files."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.

Registry GlamaPublisher brazaoo4 · publishing for 1 daysInstalls 0Last detonated 19 h ago

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.

$vet-skills run --net declared -- <the server's command>

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Remote installer piped to shellsrc/onboarding/bundles.py:215 · Remote installer piped to shellf" 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.
AST07
MEDIUM
Remote installer piped to shellsrc/onboarding/scripts_setup.py:272 · Remote installer piped to shellUsage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File permission modification commandDockerfile:36 · File permission modification command — agent changes file ownership/permissionschown -R helios:helios /data /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Pipe-to-shell patternsrc/onboarding/scripts_setup.py:272 · Pipe-to-shell pattern — downloads and immediately executes remote codeUsage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/onboarding/scripts_setup.py:379 · MCP server using network transport (SSE/HTTP) — data sent over networkdata['mcpServers']['helios'] = {{'url': sse_url}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Remote installer piped to shellsrc/onboarding/bundles.py:47 · Remote installer piped to shellf"> - 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.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/onboarding/scripts_setup.py:137 · MCP server using network transport (SSE/HTTP) — data sent over network$claudeData.mcpServers["helios"] = @{{ command = "npx"; args = @("-y", "mcp-remote", $sseUrl) }}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathssrc/tools/admin.py:101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Configure the following in your Helios `.env` and restart Helios:\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternsrc/onboarding/scripts_uninstall.py:208 · Pipe-to-shell pattern — downloads and immediately executes remote codeUsage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandsrc/onboarding/scripts_setup.py:555 · File permission modification command — agent changes file ownership/permissionschmod +x "$SCRIPTS_DIR/helios_guard.py"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedDockerfile:22 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternsrc/routes/setup.py:64 · Pipe-to-shell pattern — downloads and immediately executes remote codeUsage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternsrc/routes/setup.py:130 · Pipe-to-shell pattern — downloads and immediately executes remote codeUsage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternsrc/onboarding/bundles.py:215 · Pipe-to-shell pattern — downloads and immediately executes remote codef" 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.
AST06
CRITICAL
Pipe-to-shell patternsrc/onboarding/bundles.py:47 · Pipe-to-shell pattern — downloads and immediately executes remote codef"> - 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.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/onboarding/scripts_setup.py:115 · MCP server using network transport (SSE/HTTP) — data sent over network$cursorData.mcpServers["helios"] = @{{ url = $sseUrl }}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
URL with embedded credentialstests/test_config.py:41 · URL with embedded credentials — may be phishing or credential leakingvalidate_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.
AST07
MEDIUM
URL to the cloud instance metadata addresstests/test_config.py:51 · URL to the cloud instance metadata address — reads the VM's credentialsvalidate_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.
AST07
MEDIUM
Remote installer piped to shelltests/routes/test_setup_routes.py:107 · Remote installer piped to shellassert "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.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/onboarding/scripts_setup.py:406 · MCP server using network transport (SSE/HTTP) — data sent over networkdata['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.
AST04
MEDIUM
URL with embedded credentialstests/test_security_audit.py:108 · URL with embedded credentials — may be phishing or credential leaking"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.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:185 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file….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.
AST01
MEDIUM
Remote installer piped to shellsrc/onboarding/scripts_uninstall.py:208 · Remote installer piped to shellUsage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Hex-encoded URLtests/test_security_audit.py:107 · Hex-encoded URL — attempt to bypass URL filtering"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.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:220 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…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.
AST01
MEDIUM
URL to the cloud instance metadata addresstests/test_security_audit.py:99 · URL to the cloud instance metadata address — reads the VM's credentials"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.
AST07
MEDIUM
URL using a raw public IP addresstests/test_security_audit.py:100 · URL using a raw public IP address — may bypass domain-based filtering"http://100.100.100.200/metadata",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_guard.py:101 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/routes/setup.py:64 · Remote installer piped to shellUsage: curl -fsSL https://<host>/setup.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedtests/test_guard.py:14 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_guard.py:71 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_guard.py:38 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/routes/setup.py:130 · Remote installer piped to shellUsage: curl -fsSL https://<host>/uninstall.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Pipe-to-shell patterntests/routes/test_setup_routes.py:107 · Pipe-to-shell pattern — downloads and immediately executes remote codeassert "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.
AST06
LOW
URL to a private-network addresstests/test_config.py:23 · URL to a private-network address — a LAN or development targetassert 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.
AST07
MEDIUM
HTTP URL with a raw public IP addresstests/test_security_audit.py:100 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot name"http://100.100.100.200/metadata",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈31 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. 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.
  3. 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.
  4. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. 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.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim brazaoo4Propose a patch to the maintainer