Skills/Glama/mdengine-mcp

mdengine-mcp@r1

CAUTION

Publisher claims: "Enables agents to inspect molecular-dynamics trajectories — frames, atom counts, elements, depth profiles, and rendered images or videos — and to run LAMMPS/ReaxFF simulations as detached background jobs that survive the server exiting, with status, logs, results, and cancellation tools. Also supports submitting decks to a hosted GPU tier or your own SSH hosts, with credit balance checks and deck preflight validation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher forcefieldsilicon · joined 0 days agoInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is mdengine-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Latin word with Cyrillic or Greek look-alike letters (homoglyph); Latin word with Cyrillic or Greek look-alike letters (homoglyph); Latin word with Cyrillic or Greek look-alike letters (homoglyph). 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
Latin word with Cyrillic or Greek look-alike letters (homoglyph)CHANGELOG.md:36 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)CHANGELOG.md:25 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddocker/runner-gpu/Dockerfile:61 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL using raw IP addressCLAUDE.md:43 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:30 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/md-survey-then-commit/SKILL.md:16 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Outbound HTTP to raw IP addressdocker/runner-gpu/livetest_ttl.sh:61 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:23 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:3 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsCLAUDE.md:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:40 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detecteddocker/runner-gpu/Dockerfile:37 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/md-survey-then-commit/SKILL.md:15 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detecteddocker/runner/Dockerfile:35 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:11 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detecteddocker/runner-gpu/Dockerfile:60 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:3 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detecteddocker/runner/Dockerfile:19 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:6 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:11 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:34 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Outbound HTTP to raw IP addressCLAUDE.md:43 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/README.md:29 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/README.md:27 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:6 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/kinetics_tramd/SKILL.md:24 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)skills/tools/fep_results/SKILL.md:39 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddocker/runner-gpu/Dockerfile:66 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL using raw IP addressdocker/runner-gpu/livetest_ttl.sh:61 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commanddocker/runner-gpu/runner.sh:69 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commanddocker/runner-gpu/livetest_ttl.sh:57 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detecteddocker/runner-openmm/Dockerfile:12 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionmcpb/manifest.json:65 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:895 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddocker/runner-gpu/start.sh:11 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddocker/runner-openmm/runner.sh:69 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commanddocker/runner-openmm/start.sh:11 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddocker/runner-openmm/Dockerfile:24 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:1055 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/tools/fep_results/SKILL.md:14 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:1054 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:1030 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:900 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:1035 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:888 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)docs/manual/html/tools.html:1173 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈18,797 tok
21 files · 80 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

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim forcefieldsilicon: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  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. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Destructive file system command detected≈ +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 forcefieldsiliconPropose a patch to the maintainer