Skills/Glama/speculab-mcp

speculab-mcp@r1

CAUTION· install only

Publisher claims: "Enables agents to perform autonomous multi-angle specular glare healing and planar foil defect metrology by ranking candidate views, fusing glare-free views, and finalizing inspection or escalating unresolved cases through MCP tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher arulmuruganmcse2024-tech · publishing for 1 daysInstalls 0Last detonated 19 h ago

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
no credential variables read in the code
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$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 speculab-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 2026-11-13 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: Privileged sudo command; Privileged sudo command; URL to the cloud instance metadata address. 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
Privileged sudo commandscripts/deploy_systemd.sh:47 · Privileged sudo command — agent may execute with elevated privilegesecho "Service ${SERVICE_NAME} deployed. Start with: sudo systemctl start ${SERVICE_NAME}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandscripts/deploy_systemd.sh:46 · Privileged sudo command — agent may execute with elevated privilegessudo systemctl enable "${SERVICE_NAME}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification command.github/workflows/arm64_and_x86_benchmark.yml:57 · File permission modification command — agent changes file ownership/permissionschmod +x scripts/verify_cool.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
URL to the cloud instance metadata addressscripts/verify_cool.sh:28 · URL to the cloud instance metadata address — reads the VM's credentialsRAW_AMI=$(curl -s --connect-timeout 1 -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/ami-id 2>/dev/null || true)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actioncompare_benchmarks.py:226 · File type combined with upload action — agent may exfiltrate local data filesparser.add_argument("--output", type=str, default="benchmark_comparison.json", help="Output comparison JSON path")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedcheck_env.py:36 · Python subprocess execution detectedres = subprocess.run([candidate] + sys.argv, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
URL to the cloud instance metadata addressscripts/verify_cool.sh:22 · URL to the cloud instance metadata address — reads the VM's credentialsTOKEN=$(curl -s --connect-timeout 1 -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 21600" 2>/dev/null || true)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionscripts/pilot_physics_check.py:195 · File type combined with upload action — agent may exfiltrate local data filesparser.add_argument("--output-report", type=str, default="logs/pilot_physics_report.json", help="Output JSON path")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Privileged sudo command.github/workflows/arm64_and_x86_benchmark.yml:37 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y libgl1 libglib2.0-0 curlFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/conftest.py:25 · Python subprocess execution detectedres = subprocess.run(cmd, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandscripts/deploy_systemd.sh:25 · Privileged sudo command — agent may execute with elevated privilegessudo tee "$SERVICE_FILE" > /dev/null <<EOFFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/run_3way_graviton.sh:31 · File type combined with upload action — agent may exfiltrate local data filespython3 compare_benchmarks.py --inputs benchmark_graviton_cool.json benchmark_graviton_stock.json --output benchmark_comparison.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
URL to the cloud instance metadata addressscripts/verify_cool.sh:24 · URL to the cloud instance metadata address — reads the VM's credentialsRAW_INST=$(curl -s --connect-timeout 1 -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/instance-type 2>/dev/null || true)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Privileged sudo commandscripts/deploy_systemd.sh:45 · Privileged sudo command — agent may execute with elevated privilegessudo systemctl daemon-reloadFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/capture_gallery.py:146 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/bootstrap.py:45 · Python subprocess execution detectedres = subprocess.run([candidate] + sys.argv, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/arm64_and_x86_benchmark.yml:36 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/capture_gallery.py:53 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈44 tok
1 file · 57 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. URL to the cloud instance metadata address≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim arulmuruganmcse2024-tech: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim arulmuruganmcse2024-techPropose a patch to the maintainer