Skills/ClawHub/cite-holmes

cite-holmes@6.7.0

VERIFIED· install only

Publisher claims: "Deep research with machine-verified citations" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher docsor1212 · publishing for 99 daysInstalls 2,817Last detonated 31 min ago
$clawhub install cite-holmes
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 26 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 6.5.0

vet-skills diff cite-holmes 6.5.0 6.7.0

In the sandbox, this version reached for nothing 6.5.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 86/100 (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 · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessbundled script run in the sandbox with no arguments
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessbundled script run in the sandbox with no arguments
0.9sprocessbundled script run in the sandbox with no arguments
1.1sprocessbundled script run in the sandbox with no arguments
1.3sprocessexited 2: ❌ 需要 --refs 或 --claims 之一;--check-document 指向含「参考文献」节的文档(v4.4.0 单文件模式);--discover 主题检索(v4.5.0 文献发现);或 --demo 零门槛体验
1.3sprocess8 of 26 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.3sprocessscript backend runs setup only
1.3sprocessscript backend runs setup only
1.3sprocessno install scripts to re-run

Static findings

MEDIUM
Privileged sudo commandtests/test_v120.py:222 · Privileged sudo command — agent may execute with elevated privileges"sudo ", "set" + "uid", "StrictHost" + "KeyChecking"]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtools/selfcheck.py:157 · Python subprocess execution detectedrc = subprocess.run(["bash", rt, "--shipped"], capture_output=True, text=True, timeout=600)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_v60200.py:68 · Python subprocess execution detectedrc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL to the cloud instance metadata addresstests/test_v60600.py:55 · URL to the cloud instance metadata address — reads the VM's credentialsfor bad in ("http://127.0.0.1/x", "http://169.254.169.254/meta",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtools/selfcheck.py:137 · Python subprocess execution detectedrc = 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/selfcheck.py:88 · Python subprocess execution detectedrc = 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_v60100.py:160 · Python subprocess execution detectedr = subprocess.run([sys.executable,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_v60500.py:124 · Python subprocess execution detectedr = 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_v60300.py:26 · Python subprocess execution detectedr = subprocess.run([sys.executable, NETCHECK, "--help"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_v60500.py:174 · Python subprocess execution detectedr = 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/netcheck.py:62 · Python subprocess execution detectedp = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_v60000.py:93 · Dynamic module loadingmod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagetools/agentskills_check.py:116 · npx invocation of non-well-known package — may execute untrusted code" .claude/skills/<name>/ 均可被发现;安装 npx skillsadd <owner/repo>"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Dynamic module loadingmcp/verify_refs.py:88 · Dynamic module loading (importlib.util.module_from_spec via alias)_mod = _ilu.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/verify_refs.py:90 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(_mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingmcp/verify_refs.py:90 · Dynamic module loading (importlib.loader.exec_module via provenance)_spec.loader.exec_module(_mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_v60500.py:149 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(m)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_v60500.py:137 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(m)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_v60500.py:148 · Dynamic module loading (importlib.util.module_from_spec via alias)m = util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagetools/agentskills_check.py:112 · npx invocation of non-well-known package — may execute untrusted code# npx skillsadd <owner/repo> 安装;agentskills.io 为开放标准规范)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Dynamic module loadingscripts/verify_refs.py:88 · Dynamic module loading (importlib.util.module_from_spec via alias)_mod = _ilu.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_v60000.py:98 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_v60500.py:136 · Dynamic module loading (importlib.util.module_from_spec via alias)m = util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,889 tok
1 file · 86 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.