Skills/Glama/gnomancer

gnomancer@0.5.1

VERIFIED· not started

Publisher claims: "Analyzes a consumer raw DNA file (AncestryDNA, 23andMe, MyHeritage, FTDNA, LivingDNA, VCF) entirely on the user's machine: Y and mtDNA haplogroups, traits, ClinVar scan, PharmCAT pharmacogenomics, and a plain-language report. Tools: analyze, summary, section, lookup, narrative_prompt/set_narrative, clinvar_findings, pharmacogenomics. Nothing is uploaded." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher codebase · publishing for 12 daysInstalls 0Last detonated 7d ago
$npx skills add gnomancer
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Verified 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try gnomancer` runs it now and prints the full answer.

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1:
0.2sprocessdependency install exit 1
0.3sprocessexec /usr/bin/date
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/gnomancer
0.3sclaimedno tools/list reply (exit 0)
0.3sprocessscript backend runs setup only
0.3sprocesssecond launch, clock +45 days, CI unset
0.4sprocessexec /usr/bin/faketime
0.4sprocessexec /usr/bin/dirname
0.4sprocessexec .venv/bin/pip
0.4sprocessexited 127: ./setup.sh: line 8: .venv/bin/pip: No such file or directory

Static findings

MEDIUM
Python subprocess execution detectedgnomancer/mcp_server.py:59 · Python subprocess execution detectedreturn subprocess.run(cmd + args, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/haplogroups.py:42 · Python subprocess execution detectedp = subprocess.run([exe, "-i", str(genos), "-o", str(ydir), "--haplogroup_paths", "--der_snps_detail",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)gnomancer/mcp_server.py:38 · MCP server using network transport (SSE/HTTP) — data sent over networkserver = MCPServer("gnomancer", version=__version__, instructions=INSTRUCTIONS, website_url="https://gnomancer.com")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedgnomancer/cli.py:41 · Python subprocess execution detectedp = subprocess.run([py, "-c", code, str(inp)], capture_output=True, text=True, timeout=1800)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/haplogroups.py:105 · Python subprocess execution detectedp = subprocess.run([exe, "classify", "--tree", tree, "--in", str(hsd), "--out", str(out), "--extend-report"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Pipe-to-shell patternskills/gnomancer/SKILL.md:25 · Pipe-to-shell pattern — downloads and immediately executes remote code(or `curl -fsSL https://gnomancer.com/install.sh | bash`; Windows needs WSL, see https://gnomancer.com/install/).Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedgnomancer/yleaf.py:61 · Python subprocess execution detectedp = subprocess.run([exe, "-plink", str(ydir / f"{sample}.ped"), "-rg", "hg19", "-o", str(ydir / "out"), "-tree", *TREES,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/setup_cmd.py:76 · Python subprocess execution detectedr = subprocess.run([sys.executable, "-m", "pip", "install", "-q", spec], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellskills/gnomancer/SKILL.md:25 · Remote installer piped to shell(or `curl -fsSL https://gnomancer.com/install.sh | bash`; Windows needs WSL, see https://gnomancer.com/install/).Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actiontests/test_mcp.py:12 · File type combined with upload action — agent may exfiltrate local data files(d / "summary.json").write_text(json.dumps(dict(input=str(d / "nofile.txt"), args=[], glance={"who": ["Y: R-M269"]}, source="AncestryDNA",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 detectedgnomancer/pharmcat.py:76 · Python subprocess execution detectedp = subprocess.run([f"{env.get('JAVA_HOME', '')}/bin/java" if env.get("JAVA_HOME") else "java", "-jar", str(JAR),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_family.py:37 · Python subprocess execution detectedr = subprocess.run([sys.executable, "-m", "gnomancer", "family", *kits, "--names", "dad,mom,child1,stranger", "--out", str(tmp_path / "out"), "--no-haplogroups"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/conftest.py:13 · Python subprocess execution detectedsubprocess.run([sys.executable, str(ROOT / "examples" / "make_demo.py"), str(d)], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/setup_cmd.py:144 · Python subprocess execution detectedr = subprocess.run([str(venv / "bin" / "pip"), "install", "-q", "snps>=2.12", EZANCESTRY_SRC, YLEAF_SRC], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/setup_cmd.py:81 · Python subprocess execution detectedr = subprocess.run([uv, "pip", "install", "-q", "--python", sys.executable, spec], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedgnomancer/setup_cmd.py:143 · Python subprocess execution detectedsubprocess.run([py311, "-m", "venv", str(venv)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_family.py:35 · Python subprocess execution detectedsubprocess.run([sys.executable, str(ROOT / "examples" / "make_family.py"), str(tmp_path / "fam")], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,024 tok
2 files · 80 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.