Skills/Glama/glnet-mcp

glnet-mcp@r1

CAUTION· install only

Publisher claims: "Enables an agent to inspect and manage GL.iNet routers on firmware 4.x over the same JSON-RPC API the router's own admin panel uses, covering status, client lists, Wi-Fi and LAN configuration, static DHCP reservations, port forwards and reboots, plus a generic call for any method the router exposes — all without installing anything on the device." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher teejer · publishing for 6 daysInstalls 0Last detonated 5d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
GLNET_LUCI_PASSWORDGLNET_LUCI_PASSWORD_FILEGLNET_PASSWORDGLNET_PASSWORD_ENCGLNET_PASSWORD_FILEGLNET_SECRET_STOREConfiguration, not credentials: GLNET_BACKUP_DIR, GLNET_CATALOG, GLNET_HOST, GLNET_LUCI_PORT, GLNET_PORT, GLNET_SAMPLER_DB, GLNET_TIMEOUT, GLNET_USER, GLNET_VERIFY_TLS
Where it talks to
no vendor host named in the codeAlso gl-inet.com — 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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names gl-inet.com as well as its own vendor. The guard injects GLNET_LUCI_PASSWORD, GLNET_LUCI_PASSWORD_FILE, GLNET_PASSWORD, GLNET_PASSWORD_ENC, GLNET_PASSWORD_FILE, GLNET_SECRET_STORE 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 glnet-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsbackup_config.sh:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# The archive contains every Wi-Fi passphrase and /etc/shadow. This scriptFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandbackup_config.sh:117 · File permission modification command — agent changes file ownership/permissionschmod 600 "$work/jar" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandbackup_config.sh:81 · File permission modification command — agent changes file ownership/permissionschmod 700 "$work"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsserver.py:1126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# passphrase, in the clear) and /etc/shadow (the root password hash), plusFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandbackup_config.sh:110 · File permission modification command — agent changes file ownership/permissionschmod 600 "$work/form"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandseal-password.sh:9 · Privileged sudo command — agent may execute with elevated privileges# sudo usermod -aG tss $USER # then log out and back inFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedglnet-mcp-container.sh:181 · Destructive file system command detecteddocker run -i --rm \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandglnet-mcp-container.sh:118 · Privileged sudo command — agent may execute with elevated privilegesecho "glnet-mcp: TPM2 sealing needs TPM access for your user. Fix: sudo usermod -aG tss \$USER, then log out and back in." >&2Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandseal-password.sh:70 · File permission modification command — agent changes file ownership/permissionschmod 600 "$ENC"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandglnet-mcp-container.sh:87 · Process kill command — agent can terminate processes# works for processes we do not own, where `kill -0` would also report EPERM.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandglnet-mcp-container.sh:105 · Process kill command — agent can terminate processes# today instead of waiting on a logout that would also kill this session.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandserver.py:1411 · File permission modification command — agent changes file ownership/permissions# 0600 from the moment the file exists, not chmod after the fact.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionserver.py:1253 · File type combined with upload action — agent may exfiltrate local data files# write /tmp/glnet-probe.txt via cgi-io upload DENIED (path not listed)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandglnet-mcp-container.sh:131 · File permission modification command — agent changes file ownership/permissionschmod 600 "$STAGED"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandserver.py:221 · File permission modification command — agent changes file ownership/permissionsf"{self.cfg.password_file} (chmod 600)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandglnet-mcp-container.sh:37 · File permission modification command — agent changes file ownership/permissionsecho " either: $PLAIN (chmod 600)" >&2Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedbuild_catalog.py:279 · Python subprocess execution detectedsubprocess.run(["7z", "x", "-y", f"-o{out}", str(carve)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandserver.py:100 · File permission modification command — agent changes file ownership/permissionsf"glnet-mcp: WARNING {path} is mode {mode:03o}; chmod 600 it",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedbuild_catalog.py:270 · Python subprocess execution detectedsubprocess.run(["unsquashfs", "-no-progress", "-f", "-d", str(out),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandseal-password.sh:65 · File permission modification command — agent changes file ownership/permissionschmod 700 "$STORE"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandbackup_config.sh:136 · File permission modification command — agent changes file ownership/permissionschmod 700 "$OUTDIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandseal-password.sh:51 · File permission modification command — agent changes file ownership/permissionsecho " goes away. Use the plaintext file (chmod 600) instead, or enable" >&2Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandbackup_config.sh:150 · File permission modification command — agent changes file ownership/permissionschmod 600 "$out"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandglnet-mcp-container.sh:49 · File permission modification command — agent changes file ownership/permissionschmod 700 "$STAGE_DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandglnet-mcp-container.sh:202 · Process kill command — agent can terminate processeskill "$WATCHDOG_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandglnet-mcp-container.sh:157 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$BACKUP_HOST_DIR" && chmod 700 "$BACKUP_HOST_DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedbuild_catalog.py:274 · Python subprocess execution detectedsubprocess.run(["unsquashfs", "-no-progress", "-f", "-d", str(out),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈32 tok
1 file · 21 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim teejer: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim teejerPropose a patch to the maintainer