Skills/ClawHub/trusted-insurance-coach

trusted-insurance-coach@1.0.0

VERIFIED· install only

Publisher claims: "Reviews insurance documents to explain coverage, exclusions, disclosure, and claims requirements, and create practical checklists without judging products." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher liujycode · publishing for 22 daysInstalls 10Last detonated 25 h ago
$clawhub install trusted-insurance-coach
WatchReport an issue

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

Is [email protected] 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 87/100 (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 · 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

MEDIUM
Python subprocess execution detectedtrusted-insurance-coach/scripts/selfcheck.py:46 · Python subprocess execution detectedreturn subprocess.run([PY] + args, cwd=ROOT, capture_output=True, text=True, **kw)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontrusted-insurance-coach/skills/ins-policy-checkup/scripts/policy_review.py:25 · File type combined with upload action — agent may exfiltrate local data filespython3 policy_review.py --income 30 --input policies.json --output review.mdFix: 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 actiontrusted-insurance-coach/skills/ins-policy-checkup/scripts/policy_review.py:24 · File type combined with upload action — agent may exfiltrate local data filespython3 policy_review.py --input policies.json --output review.mdFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtrusted-insurance-coach/scripts/usertest.py:35 · Python subprocess execution detectedr = subprocess.run([PY, script] + list(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
File type combined with upload actiontrusted-insurance-coach/skills/ins-policy-checkup/scripts/policy_review.py:294 · File type combined with upload action — agent may exfiltrate local data files" · 或者放到当前目录,用文件名就行:--input 我的保单.json".format(args.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 detectedtrusted-insurance-coach/scripts/agentprobe.py:113 · Python subprocess execution detectedr = subprocess.run([sys.executable, SCAN, "--text", text],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontrusted-insurance-coach/skills/ins-policy-checkup/scripts/policy_review.py:299 · File type combined with upload action — agent may exfiltrate local data files" 请指向里面的那个 .json 文件,例如:--input {}/我的保单.json".format(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
≈8,510 tok
6 files · 100 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.

trusted-insurance-coach@1.0.0 safety verdict: Verified (install only) — KillerSkills