Skills/Glama/agentsql

agentsql@0.3.0a1

VERIFIED· not started

Publisher claims: "Enables cooperating AI agents to manage versioned files and JSON key-value state, record tool-call history, and publish changes atomically after dependency validation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher grishahq · publishing for 0 daysInstalls 0Last detonated 8 h ago
$npx skills add agentsql
WatchReport an issue

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: 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

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
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. 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 [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 2026-11-14 and scored it 85/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_cli.py:26 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_chaos.py:164 · File type combined with upload action — agent may exfiltrate local data filesself.assertEqual(snapshot.list_files(), ["left.txt", f"outputs/{winner}.txt", "right.txt"])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_chaos.py:261 · File type combined with upload action — agent may exfiltrate local data filesself.assertEqual(snapshot.list_files(), ["left.txt", "output-one.txt", "output-two.txt"])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_chaos.py:273 · File type combined with upload action — agent may exfiltrate local data filesself.assertEqual(history[-1]["paths"], ["left.txt", "output-one.txt", "output-two.txt", "right.txt"])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/agentsql/demo.py:55 · File type combined with upload action — agent may exfiltrate local data files), "The rejection must identify the tracked prices.csv input"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 detectedsrc/agentsql/runner.py:76 · Python subprocess execution detectedprocess = subprocess.Popen(command, cwd=directory, env=environment,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_operations_cli.py:111 · Python subprocess execution detectedchecked = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_workspace.py:154 · File type combined with upload action — agent may exfiltrate local data filesbranch.write_text("z-failure.txt", "second pending output")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 detectedtests/test_platform_cli.py:23 · Python subprocess execution detectedcompleted = subprocess.run([sys.executable, "-m", "agentsql", "-w",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_model.py:165 · File type combined with upload action — agent may exfiltrate local data filesstale.write("results/a.txt", b"derived from old input")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 detectedtests/test_scenarios.py:18 · Python subprocess execution detectedresult = 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_platform_demo.py:21 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_operations_cli.py:28 · File type combined with upload action — agent may exfiltrate local data files(self.source / "input.txt").write_text("Original input\n", encoding="utf-8")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_workspace.py:182 · File type combined with upload action — agent may exfiltrate local data filesself.assertEqual(reopened.snapshot().read_text("a-first.txt"), "first pending output")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 detectedtests/test_project_integration.py:22 · Python subprocess execution detectedrun = subprocess.run(command, cwd=root, capture_output=True, text=True, timeout=20)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_operations_cli.py:83 · File type combined with upload action — agent may exfiltrate local data filesworker.write_text("result.txt", "Based on original input")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_operations_cli.py:86 · File type combined with upload action — agent may exfiltrate local data filesupdater.write_text("input.txt", "Changed input")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiontests/test_model.py:166 · File type combined with upload action — agent may exfiltrate local data filesworkspace.get_branch(stale_name).write_bytes("results/a.txt", b"derived from old input")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 detectedtests/test_platform_demo.py:70 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/verify_release.py:43 · Python subprocess execution detectedresult = subprocess.run(command, cwd=directory, env=env, 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 detectedtests/test_operations_cli.py:201 · Python subprocess execution detectedraw = subprocess.run(command + ["read", worker.name, "résultat.md"], env=environment,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_workspace.py:264 · File type combined with upload action — agent may exfiltrate local data filesbranch.write_text("decision.txt", "No optional input was available")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 detectedtests/test_platform_demo.py:57 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_state.py:19 · File type combined with upload action — agent may exfiltrate local data filesbranch.write_text(f"{name}.txt", "atomic output")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 detectedtests/test_project_integration.py:33 · Python subprocess execution detectedrepeated = subprocess.run(command, cwd=root, capture_output=True, text=True, timeout=20)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_operations_cli.py:33 · Python subprocess execution detectedresult = 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_scenarios.py:39 · Python subprocess execution detectedresult = 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_server.py:209 · Python subprocess execution detectedcompleted = subprocess.run([sys.executable, "-c", script, str(self.database)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_on_call_race.py:23 · Python subprocess execution detectedreturn subprocess.run([sys.executable, str(EXAMPLE), *arguments], cwd=directory,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_operations_cli.py:197 · Python subprocess execution detectedfailed_diff = subprocess.run(command + ["diff", worker.name], env=environment,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_runner.py:90 · Python subprocess execution detected"subprocess.Popen([sys.executable,'-c',"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_operations_cli.py:193 · Python subprocess execution detectedinspected = subprocess.run(command + ["inspect", worker.name], env=environment,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_workspace.py:183 · File type combined with upload action — agent may exfiltrate local data filesself.assertEqual(reopened.snapshot().read_text("z-failure.txt"), "second pending output")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstests/test_runner.py:288 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Path('good').write_text('partial'); Path('unsafe').symlink_to('/etc/passwd')")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_workspace.py:153 · File type combined with upload action — agent may exfiltrate local data filesbranch.write_text("a-first.txt", "first pending output")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈33 tok
1 file · 54 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.

agentsql@0.3.0a1 safety verdict: Verified (not started) — KillerSkills